diff --git a/components/Settings/SettingsModal.tsx b/components/Settings/SettingsModal.tsx index 70a5c50..da7ebe3 100644 --- a/components/Settings/SettingsModal.tsx +++ b/components/Settings/SettingsModal.tsx @@ -38,10 +38,15 @@ import { useDebouncedValue } from '@mantine/hooks'; import { deleteModel, getInstalledModels, pullModel, type OllamaModel } from '@/app/actions/ollama'; // Type for the scraped models JSON +interface ModelInfo { + tags: string[]; + capabilities: string[]; +} + interface OllamaModelsData { generatedAt: string; modelCount: number; - models: Record; + models: Record; } interface User { @@ -540,17 +545,41 @@ export function SettingsModal({ }} > {paginatedModels.map((modelName) => { - const tags = availableModels?.models[modelName] || []; + const modelInfo = availableModels?.models[modelName]; + const tags = modelInfo?.tags || []; + const capabilities = modelInfo?.capabilities || []; const installedTags = getInstalledTags(modelName); return ( - - - {modelName} - - + + + + {modelName} + + {capabilities.map((cap) => ( + + {cap} + + ))} + + {tags.length} tags diff --git a/public/ollama-models.json b/public/ollama-models.json index efccab1..16f7dd1 100644 --- a/public/ollama-models.json +++ b/public/ollama-models.json @@ -1,7352 +1,8167 @@ { - "generatedAt": "2026-01-15T13:20:34.921Z", + "generatedAt": "2026-01-15T13:45:44.023Z", "modelCount": 205, "models": { - "nemotron-3-nano": [ - "latest", - "30b", - "30b-a3b-q4_K_M", - "30b-a3b-q8_0", - "30b-a3b-fp16", - "30b-cloud" - ], - "functiongemma": [ - "latest", - "270m", - "270m-it-q8_0", - "270m-it-fp16" - ], - "olmo-3": [ - "latest", - "7b", - "32b", - "7b-instruct", - "7b-instruct-q4_K_M", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "7b-think", - "7b-think-q4_K_M", - "7b-think-q8_0", - "7b-think-fp16", - "32b-think", - "32b-think-q4_K_M", - "32b-think-q8_0", - "32b-think-fp16" - ], - "gemini-3-flash-preview": [ - "latest", - "cloud" - ], - "devstral-small-2": [ - "latest", - "24b", - "24b-cloud", - "24b-instruct-2512-q4_K_M", - "24b-instruct-2512-q8_0", - "24b-instruct-2512-fp16" - ], - "devstral-2": [ - "latest", - "123b", - "123b-cloud", - "123b-instruct-2512-q4_K_M", - "123b-instruct-2512-q8_0", - "123b-instruct-2512-fp16" - ], - "ministral-3": [ - "latest", - "3b", - "8b", - "14b", - "3b-cloud", - "3b-instruct-2512-q4_K_M", - "3b-instruct-2512-q8_0", - "3b-instruct-2512-fp16", - "8b-cloud", - "8b-instruct-2512-q4_K_M", - "8b-instruct-2512-q8_0", - "8b-instruct-2512-fp16", - "14b-cloud", - "14b-instruct-2512-q4_K_M", - "14b-instruct-2512-q8_0", - "14b-instruct-2512-fp16" - ], - "qwen3-vl": [ - "latest", - "2b", - "4b", - "8b", - "30b", - "32b", - "235b", - "2b-instruct", - "2b-instruct-q4_K_M", - "2b-instruct-q8_0", - "2b-instruct-bf16", - "2b-thinking", - "2b-thinking-q4_K_M", - "2b-thinking-q8_0", - "2b-thinking-bf16", - "4b-instruct", - "4b-instruct-q4_K_M", - "4b-instruct-q8_0", - "4b-instruct-bf16", - "4b-thinking", - "4b-thinking-q4_K_M", - "4b-thinking-q8_0", - "4b-thinking-bf16", - "8b-instruct", - "8b-instruct-q4_K_M", - "8b-instruct-q8_0", - "8b-instruct-bf16", - "8b-thinking", - "8b-thinking-q4_K_M", - "8b-thinking-q8_0", - "8b-thinking-bf16", - "30b-a3b", - "30b-a3b-instruct", - "30b-a3b-instruct-q4_K_M", - "30b-a3b-instruct-q8_0", - "30b-a3b-instruct-bf16", - "30b-a3b-thinking", - "30b-a3b-thinking-q4_K_M", - "30b-a3b-thinking-q8_0", - "30b-a3b-thinking-bf16", - "32b-instruct", - "32b-instruct-q4_K_M", - "32b-instruct-q8_0", - "32b-instruct-bf16", - "32b-thinking", - "32b-thinking-q4_K_M", - "32b-thinking-q8_0", - "32b-thinking-bf16", - "235b-a22b", - "235b-a22b-instruct", - "235b-a22b-instruct-q4_K_M", - "235b-a22b-instruct-q8_0", - "235b-a22b-instruct-bf16", - "235b-a22b-thinking", - "235b-a22b-thinking-q4_K_M", - "235b-a22b-thinking-q8_0", - "235b-a22b-thinking-bf16", - "235b-cloud", - "235b-instruct-cloud" - ], - "gpt-oss": [ - "latest", - "20b", - "120b", - "20b-cloud", - "120b-cloud" - ], - "deepseek-r1": [ - "latest", - "1.5b", - "7b", - "8b", - "14b", - "32b", - "70b", - "671b", - "1.5b-qwen-distill-q4_K_M", - "1.5b-qwen-distill-q8_0", - "1.5b-qwen-distill-fp16", - "7b-qwen-distill-q4_K_M", - "7b-qwen-distill-q8_0", - "7b-qwen-distill-fp16", - "8b-0528-qwen3-q4_K_M", - "8b-0528-qwen3-q8_0", - "8b-0528-qwen3-fp16", - "8b-llama-distill-q4_K_M", - "8b-llama-distill-q8_0", - "8b-llama-distill-fp16", - "14b-qwen-distill-q4_K_M", - "14b-qwen-distill-q8_0", - "14b-qwen-distill-fp16", - "32b-qwen-distill-q4_K_M", - "32b-qwen-distill-q8_0", - "32b-qwen-distill-fp16", - "70b-llama-distill-q4_K_M", - "70b-llama-distill-q8_0", - "70b-llama-distill-fp16", - "671b-0528-q4_K_M", - "671b-0528-q8_0", - "671b-0528-fp16", - "671b-q4_K_M", - "671b-q8_0", - "671b-fp16" - ], - "qwen3-coder": [ - "latest", - "30b", - "480b", - "30b-a3b-q4_K_M", - "30b-a3b-q8_0", - "30b-a3b-fp16", - "480b-a35b-q4_K_M", - "480b-a35b-q8_0", - "480b-a35b-fp16", - "480b-cloud" - ], - "gemma3": [ - "latest", - "270m", - "1b", - "4b", - "12b", - "27b", - "270m-it-qat", - "270m-it-q8_0", - "270m-it-fp16", - "270m-it-bf16", - "1b-it-qat", - "1b-it-q4_K_M", - "1b-it-q8_0", - "1b-it-fp16", - "4b-cloud", - "4b-it-qat", - "4b-it-q4_K_M", - "4b-it-q8_0", - "4b-it-fp16", - "12b-cloud", - "12b-it-qat", - "12b-it-q4_K_M", - "12b-it-q8_0", - "12b-it-fp16", - "27b-cloud", - "27b-it-qat", - "27b-it-q4_K_M", - "27b-it-q8_0", - "27b-it-fp16" - ], - "llama3.1": [ - "latest", - "8b", - "70b", - "405b", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-q4_0", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16", - "8b-text-q2_K", - "8b-text-q3_K_S", - "8b-text-q3_K_M", - "8b-text-q3_K_L", - "8b-text-q4_0", - "8b-text-q4_1", - "8b-text-q4_K_S", - "8b-text-q4_K_M", - "8b-text-q5_0", - "8b-text-q5_1", - "8b-text-q5_K_S", - "8b-text-q5_K_M", - "8b-text-q6_K", - "8b-text-q8_0", - "8b-text-fp16", - "70b-instruct-q2_K", - "70b-instruct-q3_K_S", - "70b-instruct-q3_K_M", - "70b-instruct-q3_K_L", - "70b-instruct-q4_0", - "70b-instruct-q4_K_S", - "70b-instruct-q4_K_M", - "70b-instruct-q5_0", - "70b-instruct-q5_1", - "70b-instruct-q5_K_S", - "70b-instruct-q5_K_M", - "70b-instruct-q6_K", - "70b-instruct-q8_0", - "70b-instruct-fp16", - "70b-text-q2_K", - "70b-text-q3_K_S", - "70b-text-q3_K_M", - "70b-text-q3_K_L", - "70b-text-q4_0", - "70b-text-q4_1", - "70b-text-q4_K_S", - "70b-text-q4_K_M", - "70b-text-q5_0", - "70b-text-q5_1", - "70b-text-q5_K_S", - "70b-text-q5_K_M", - "70b-text-q6_K", - "70b-text-q8_0", - "70b-text-fp16", - "405b-instruct-q2_K", - "405b-instruct-q3_K_S", - "405b-instruct-q3_K_M", - "405b-instruct-q3_K_L", - "405b-instruct-q4_0", - "405b-instruct-q4_1", - "405b-instruct-q4_K_S", - "405b-instruct-q4_K_M", - "405b-instruct-q5_0", - "405b-instruct-q5_1", - "405b-instruct-q5_K_S", - "405b-instruct-q5_K_M", - "405b-instruct-q6_K", - "405b-instruct-q8_0", - "405b-instruct-fp16", - "405b-text-q2_K", - "405b-text-q3_K_S", - "405b-text-q3_K_M", - "405b-text-q3_K_L", - "405b-text-q4_0", - "405b-text-q4_1", - "405b-text-q4_K_S", - "405b-text-q4_K_M", - "405b-text-q5_0", - "405b-text-q5_1", - "405b-text-q5_K_S", - "405b-text-q5_K_M", - "405b-text-q6_K", - "405b-text-q8_0", - "405b-text-fp16" - ], - "llama3.2": [ - "latest", - "1b", - "3b", - "1b-instruct-q2_K", - "1b-instruct-q3_K_S", - "1b-instruct-q3_K_M", - "1b-instruct-q3_K_L", - "1b-instruct-q4_0", - "1b-instruct-q4_1", - "1b-instruct-q4_K_S", - "1b-instruct-q4_K_M", - "1b-instruct-q5_0", - "1b-instruct-q5_1", - "1b-instruct-q5_K_S", - "1b-instruct-q5_K_M", - "1b-instruct-q6_K", - "1b-instruct-q8_0", - "1b-instruct-fp16", - "1b-text-q2_K", - "1b-text-q3_K_S", - "1b-text-q3_K_M", - "1b-text-q3_K_L", - "1b-text-q4_0", - "1b-text-q4_1", - "1b-text-q4_K_S", - "1b-text-q4_K_M", - "1b-text-q5_0", - "1b-text-q5_1", - "1b-text-q5_K_S", - "1b-text-q5_K_M", - "1b-text-q6_K", - "1b-text-q8_0", - "1b-text-fp16", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16", - "3b-text-q2_K", - "3b-text-q3_K_S", - "3b-text-q3_K_M", - "3b-text-q3_K_L", - "3b-text-q4_0", - "3b-text-q4_1", - "3b-text-q4_K_S", - "3b-text-q4_K_M", - "3b-text-q5_0", - "3b-text-q5_1", - "3b-text-q5_K_S", - "3b-text-q5_K_M", - "3b-text-q6_K", - "3b-text-q8_0", - "3b-text-fp16" - ], - "nomic-embed-text": [ - "latest", - "v1.5", - "137m-v1.5-fp16" - ], - "mistral": [ - "latest", - "instruct", - "text", - "v0.1", - "v0.2", - "v0.3", - "7b", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-v0.2-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-v0.2-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-v0.2-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-v0.2-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-v0.2-q4_0", - "7b-instruct-q4_1", - "7b-instruct-v0.2-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-v0.2-q4_K_S", - "7b-instruct-v0.2-q4_K_M", - "7b-instruct-v0.2-q5_0", - "7b-instruct-v0.2-q5_1", - "7b-instruct-v0.2-q5_K_S", - "7b-instruct-v0.2-q5_K_M", - "7b-instruct-v0.2-q6_K", - "7b-instruct-v0.2-q8_0", - "7b-instruct-v0.2-fp16", - "7b-instruct-v0.3-q2_K", - "7b-instruct-v0.3-q3_K_S", - "7b-instruct-v0.3-q3_K_M", - "7b-instruct-v0.3-q3_K_L", - "7b-instruct-v0.3-q4_0", - "7b-instruct-v0.3-q4_1", - "7b-instruct-v0.3-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-v0.3-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-v0.3-q5_0", - "7b-instruct-q5_1", - "7b-instruct-v0.3-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-v0.3-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-v0.3-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-v0.3-q6_K", - "7b-instruct-q8_0", - "7b-instruct-v0.3-q8_0", - "7b-instruct-fp16", - "7b-instruct-v0.3-fp16", - "7b-text", - "7b-text-q2_K", - "7b-text-v0.2-q2_K", - "7b-text-q3_K_S", - "7b-text-v0.2-q3_K_S", - "7b-text-q3_K_M", - "7b-text-v0.2-q3_K_M", - "7b-text-q3_K_L", - "7b-text-v0.2-q3_K_L", - "7b-text-q4_0", - "7b-text-v0.2-q4_0", - "7b-text-q4_1", - "7b-text-v0.2-q4_1", - "7b-text-q4_K_S", - "7b-text-v0.2-q4_K_S", - "7b-text-q4_K_M", - "7b-text-v0.2-q4_K_M", - "7b-text-q5_0", - "7b-text-v0.2-q5_0", - "7b-text-q5_1", - "7b-text-v0.2-q5_1", - "7b-text-q5_K_S", - "7b-text-v0.2-q5_K_S", - "7b-text-q5_K_M", - "7b-text-v0.2-q5_K_M", - "7b-text-q6_K", - "7b-text-v0.2-q6_K", - "7b-text-q8_0", - "7b-text-v0.2-q8_0", - "7b-text-fp16", - "7b-text-v0.2-fp16" - ], - "qwen2.5": [ - "latest", - "0.5b", - "1.5b", - "3b", - "7b", - "14b", - "32b", - "72b", - "0.5b-base", - "0.5b-base-q2_K", - "0.5b-base-q3_K_S", - "0.5b-base-q3_K_M", - "0.5b-base-q3_K_L", - "0.5b-base-q4_0", - "0.5b-base-q4_1", - "0.5b-base-q4_K_S", - "0.5b-base-q4_K_M", - "0.5b-base-q5_0", - "0.5b-base-q5_1", - "0.5b-base-q5_K_S", - "0.5b-base-q8_0", - "0.5b-instruct", - "0.5b-instruct-q2_K", - "0.5b-instruct-q3_K_S", - "0.5b-instruct-q3_K_M", - "0.5b-instruct-q3_K_L", - "0.5b-instruct-q4_0", - "0.5b-instruct-q4_1", - "0.5b-instruct-q4_K_S", - "0.5b-instruct-q4_K_M", - "0.5b-instruct-q5_0", - "0.5b-instruct-q5_1", - "0.5b-instruct-q5_K_S", - "0.5b-instruct-q5_K_M", - "0.5b-instruct-q6_K", - "0.5b-instruct-q8_0", - "0.5b-instruct-fp16", - "1.5b-instruct", - "1.5b-instruct-q2_K", - "1.5b-instruct-q3_K_S", - "1.5b-instruct-q3_K_M", - "1.5b-instruct-q3_K_L", - "1.5b-instruct-q4_0", - "1.5b-instruct-q4_1", - "1.5b-instruct-q4_K_S", - "1.5b-instruct-q4_K_M", - "1.5b-instruct-q5_0", - "1.5b-instruct-q5_1", - "1.5b-instruct-q5_K_S", - "1.5b-instruct-q5_K_M", - "1.5b-instruct-q6_K", - "1.5b-instruct-q8_0", - "1.5b-instruct-fp16", - "3b-instruct", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "14b-instruct", - "14b-instruct-q2_K", - "14b-instruct-q3_K_S", - "14b-instruct-q3_K_M", - "14b-instruct-q3_K_L", - "14b-instruct-q4_0", - "14b-instruct-q4_1", - "14b-instruct-q4_K_S", - "14b-instruct-q4_K_M", - "14b-instruct-q5_0", - "14b-instruct-q5_1", - "14b-instruct-q5_K_S", - "14b-instruct-q5_K_M", - "14b-instruct-q6_K", - "14b-instruct-q8_0", - "14b-instruct-fp16", - "32b-instruct", - "32b-instruct-q2_K", - "32b-instruct-q3_K_S", - "32b-instruct-q3_K_M", - "32b-instruct-q3_K_L", - "32b-instruct-q4_0", - "32b-instruct-q4_1", - "32b-instruct-q4_K_S", - "32b-instruct-q4_K_M", - "32b-instruct-q5_0", - "32b-instruct-q5_1", - "32b-instruct-q5_K_S", - "32b-instruct-q5_K_M", - "32b-instruct-q6_K", - "32b-instruct-q8_0", - "32b-instruct-fp16", - "72b-instruct", - "72b-instruct-q2_K", - "72b-instruct-q3_K_S", - "72b-instruct-q3_K_M", - "72b-instruct-q3_K_L", - "72b-instruct-q4_0", - "72b-instruct-q4_1", - "72b-instruct-q4_K_S", - "72b-instruct-q4_K_M", - "72b-instruct-q5_0", - "72b-instruct-q5_1", - "72b-instruct-q5_K_S", - "72b-instruct-q5_K_M", - "72b-instruct-q6_K", - "72b-instruct-q8_0", - "72b-instruct-fp16" - ], - "qwen3": [ - "latest", - "0.6b", - "1.7b", - "4b", - "8b", - "14b", - "30b", - "32b", - "235b", - "0.6b-q4_K_M", - "0.6b-q8_0", - "0.6b-fp16", - "1.7b-q4_K_M", - "1.7b-q8_0", - "1.7b-fp16", - "4b-instruct", - "4b-instruct-2507-q4_K_M", - "4b-instruct-2507-q8_0", - "4b-instruct-2507-fp16", - "4b-thinking", - "4b-thinking-2507-q4_K_M", - "4b-thinking-2507-q8_0", - "4b-thinking-2507-fp16", - "4b-q4_K_M", - "4b-q8_0", - "4b-fp16", - "8b-q4_K_M", - "8b-q8_0", - "8b-fp16", - "14b-q4_K_M", - "14b-q8_0", - "14b-fp16", - "30b-a3b", - "30b-a3b-instruct-2507-q4_K_M", - "30b-a3b-q4_K_M", - "30b-a3b-instruct-2507-q8_0", - "30b-a3b-thinking-2507-q4_K_M", - "30b-a3b-q8_0", - "30b-a3b-thinking-2507-q8_0", - "30b-a3b-fp16", - "30b-a3b-instruct-2507-fp16", - "30b-a3b-thinking-2507-fp16", - "30b-instruct", - "30b-thinking", - "32b-q4_K_M", - "32b-q8_0", - "32b-fp16", - "235b-a22b", - "235b-a22b-instruct-2507-q4_K_M", - "235b-a22b-q4_K_M", - "235b-a22b-instruct-2507-q8_0", - "235b-a22b-thinking-2507-q4_K_M", - "235b-a22b-q8_0", - "235b-a22b-thinking-2507-q8_0", - "235b-a22b-fp16", - "235b-a22b-thinking-2507-fp16", - "235b-instruct", - "235b-thinking" - ], - "phi3": [ - "latest", - "instruct", - "medium", - "mini", - "3.8b", - "14b", - "3.8b-instruct", - "3.8b-mini-128k-instruct-q2_K", - "3.8b-mini-128k-instruct-q3_K_S", - "3.8b-mini-128k-instruct-q3_K_M", - "3.8b-mini-128k-instruct-q3_K_L", - "3.8b-mini-128k-instruct-q4_0", - "3.8b-mini-128k-instruct-q4_1", - "3.8b-mini-128k-instruct-q4_K_S", - "3.8b-mini-128k-instruct-q4_K_M", - "3.8b-mini-128k-instruct-q5_0", - "3.8b-mini-128k-instruct-q5_1", - "3.8b-mini-128k-instruct-q5_K_S", - "3.8b-mini-128k-instruct-q5_K_M", - "3.8b-mini-128k-instruct-q6_K", - "3.8b-mini-128k-instruct-q8_0", - "3.8b-mini-128k-instruct-fp16", - "3.8b-mini-4k-instruct-q2_K", - "3.8b-mini-4k-instruct-q3_K_S", - "3.8b-mini-4k-instruct-q3_K_M", - "3.8b-mini-4k-instruct-q3_K_L", - "3.8b-mini-4k-instruct-q4_0", - "3.8b-mini-4k-instruct-q4_1", - "3.8b-mini-4k-instruct-q4_K_S", - "3.8b-mini-4k-instruct-q4_K_M", - "3.8b-mini-4k-instruct-q5_0", - "3.8b-mini-4k-instruct-q5_1", - "3.8b-mini-4k-instruct-q5_K_S", - "3.8b-mini-4k-instruct-q5_K_M", - "3.8b-mini-4k-instruct-q6_K", - "3.8b-mini-4k-instruct-q8_0", - "3.8b-mini-4k-instruct-fp16", - "14b-instruct", - "14b-medium-128k-instruct-q2_K", - "14b-medium-128k-instruct-q3_K_S", - "14b-medium-128k-instruct-q3_K_M", - "14b-medium-128k-instruct-q3_K_L", - "14b-medium-128k-instruct-q4_0", - "14b-medium-128k-instruct-q4_1", - "14b-medium-128k-instruct-q4_K_S", - "14b-medium-128k-instruct-q4_K_M", - "14b-medium-128k-instruct-q5_0", - "14b-medium-128k-instruct-q5_1", - "14b-medium-128k-instruct-q5_K_S", - "14b-medium-128k-instruct-q5_K_M", - "14b-medium-128k-instruct-q6_K", - "14b-medium-128k-instruct-q8_0", - "14b-medium-128k-instruct-fp16", - "14b-medium-4k-instruct-q2_K", - "14b-medium-4k-instruct-q3_K_S", - "14b-medium-4k-instruct-q3_K_M", - "14b-medium-4k-instruct-q3_K_L", - "14b-medium-4k-instruct-q4_0", - "14b-medium-4k-instruct-q4_1", - "14b-medium-4k-instruct-q4_K_S", - "14b-medium-4k-instruct-q4_K_M", - "14b-medium-4k-instruct-q5_0", - "14b-medium-4k-instruct-q5_1", - "14b-medium-4k-instruct-q5_K_S", - "14b-medium-4k-instruct-q5_K_M", - "14b-medium-4k-instruct-q6_K", - "14b-medium-4k-instruct-q8_0", - "14b-medium-4k-instruct-fp16", - "medium-128k", - "medium-4k", - "mini-128k", - "mini-4k" - ], - "llama3": [ - "latest", - "instruct", - "text", - "8b", - "70b", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-q4_0", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16", - "8b-text", - "8b-text-q2_K", - "8b-text-q3_K_S", - "8b-text-q3_K_M", - "8b-text-q3_K_L", - "8b-text-q4_0", - "8b-text-q4_1", - "8b-text-q4_K_S", - "8b-text-q4_K_M", - "8b-text-q5_0", - "8b-text-q5_1", - "8b-text-q5_K_S", - "8b-text-q5_K_M", - "8b-text-q6_K", - "8b-text-q8_0", - "8b-text-fp16", - "70b-instruct", - "70b-instruct-q2_K", - "70b-instruct-q3_K_S", - "70b-instruct-q3_K_M", - "70b-instruct-q3_K_L", - "70b-instruct-q4_0", - "70b-instruct-q4_1", - "70b-instruct-q4_K_S", - "70b-instruct-q4_K_M", - "70b-instruct-q5_0", - "70b-instruct-q5_1", - "70b-instruct-q5_K_S", - "70b-instruct-q5_K_M", - "70b-instruct-q6_K", - "70b-instruct-q8_0", - "70b-instruct-fp16", - "70b-text", - "70b-text-q2_K", - "70b-text-q3_K_S", - "70b-text-q3_K_M", - "70b-text-q3_K_L", - "70b-text-q4_0", - "70b-text-q4_1", - "70b-text-q4_K_S", - "70b-text-q4_K_M", - "70b-text-q5_0", - "70b-text-q5_1", - "70b-text-q5_K_S", - "70b-text-q5_K_M", - "70b-text-q6_K", - "70b-text-q8_0", - "70b-text-fp16" - ], - "gemma2": [ - "latest", - "2b", - "9b", - "27b", - "2b-instruct-q2_K", - "2b-instruct-q3_K_S", - "2b-instruct-q3_K_M", - "2b-instruct-q3_K_L", - "2b-instruct-q4_0", - "2b-instruct-q4_1", - "2b-instruct-q4_K_S", - "2b-instruct-q4_K_M", - "2b-instruct-q5_0", - "2b-instruct-q5_1", - "2b-instruct-q5_K_S", - "2b-instruct-q5_K_M", - "2b-instruct-q6_K", - "2b-instruct-q8_0", - "2b-instruct-fp16", - "2b-text-q2_K", - "2b-text-q3_K_S", - "2b-text-q3_K_M", - "2b-text-q3_K_L", - "2b-text-q4_0", - "2b-text-q4_1", - "2b-text-q4_K_S", - "2b-text-q4_K_M", - "2b-text-q5_0", - "2b-text-q5_1", - "2b-text-q5_K_S", - "2b-text-q5_K_M", - "2b-text-q6_K", - "2b-text-q8_0", - "2b-text-fp16", - "9b-instruct-q2_K", - "9b-instruct-q3_K_S", - "9b-instruct-q3_K_M", - "9b-instruct-q3_K_L", - "9b-instruct-q4_0", - "9b-instruct-q4_1", - "9b-instruct-q4_K_S", - "9b-instruct-q4_K_M", - "9b-instruct-q5_0", - "9b-instruct-q5_1", - "9b-instruct-q5_K_S", - "9b-instruct-q5_K_M", - "9b-instruct-q6_K", - "9b-instruct-q8_0", - "9b-instruct-fp16", - "9b-text-q2_K", - "9b-text-q3_K_S", - "9b-text-q3_K_M", - "9b-text-q3_K_L", - "9b-text-q4_0", - "9b-text-q4_1", - "9b-text-q4_K_S", - "9b-text-q4_K_M", - "9b-text-q5_0", - "9b-text-q5_1", - "9b-text-q5_K_S", - "9b-text-q5_K_M", - "9b-text-q6_K", - "9b-text-q8_0", - "9b-text-fp16", - "27b-instruct-q2_K", - "27b-instruct-q3_K_S", - "27b-instruct-q3_K_M", - "27b-instruct-q3_K_L", - "27b-instruct-q4_0", - "27b-instruct-q4_1", - "27b-instruct-q4_K_S", - "27b-instruct-q4_K_M", - "27b-instruct-q5_0", - "27b-instruct-q5_1", - "27b-instruct-q5_K_S", - "27b-instruct-q5_K_M", - "27b-instruct-q6_K", - "27b-instruct-q8_0", - "27b-instruct-fp16", - "27b-text-q2_K", - "27b-text-q3_K_S", - "27b-text-q3_K_M", - "27b-text-q3_K_L", - "27b-text-q4_0", - "27b-text-q4_1", - "27b-text-q4_K_S", - "27b-text-q4_K_M", - "27b-text-q5_0", - "27b-text-q5_1", - "27b-text-q5_K_S", - "27b-text-q5_K_M", - "27b-text-q6_K", - "27b-text-q8_0", - "27b-text-fp16" - ], - "llava": [ - "latest", - "v1.6", - "7b", - "13b", - "34b", - "7b-v1.5-q2_K", - "7b-v1.5-q3_K_S", - "7b-v1.5-q3_K_M", - "7b-v1.5-q3_K_L", - "7b-v1.5-q4_0", - "7b-v1.5-q4_1", - "7b-v1.5-q4_K_S", - "7b-v1.5-q4_K_M", - "7b-v1.5-q5_0", - "7b-v1.5-q5_1", - "7b-v1.5-q5_K_S", - "7b-v1.5-q5_K_M", - "7b-v1.5-q6_K", - "7b-v1.5-q8_0", - "7b-v1.5-fp16", - "7b-v1.6", - "7b-v1.6-mistral-q2_K", - "7b-v1.6-mistral-q3_K_S", - "7b-v1.6-mistral-q3_K_M", - "7b-v1.6-mistral-q3_K_L", - "7b-v1.6-mistral-q4_0", - "7b-v1.6-mistral-q4_1", - "7b-v1.6-mistral-q4_K_S", - "7b-v1.6-mistral-q4_K_M", - "7b-v1.6-mistral-q5_0", - "7b-v1.6-mistral-q5_1", - "7b-v1.6-mistral-q5_K_S", - "7b-v1.6-mistral-q5_K_M", - "7b-v1.6-mistral-q6_K", - "7b-v1.6-mistral-q8_0", - "7b-v1.6-mistral-fp16", - "7b-v1.6-vicuna-q2_K", - "7b-v1.6-vicuna-q3_K_S", - "7b-v1.6-vicuna-q3_K_M", - "7b-v1.6-vicuna-q3_K_L", - "7b-v1.6-vicuna-q4_0", - "7b-v1.6-vicuna-q4_1", - "7b-v1.6-vicuna-q4_K_S", - "7b-v1.6-vicuna-q4_K_M", - "7b-v1.6-vicuna-q5_0", - "7b-v1.6-vicuna-q5_1", - "7b-v1.6-vicuna-q5_K_S", - "7b-v1.6-vicuna-q5_K_M", - "7b-v1.6-vicuna-q6_K", - "7b-v1.6-vicuna-q8_0", - "7b-v1.6-vicuna-fp16", - "13b-v1.5-q2_K", - "13b-v1.5-q3_K_S", - "13b-v1.5-q3_K_M", - "13b-v1.5-q3_K_L", - "13b-v1.5-q4_0", - "13b-v1.5-q4_1", - "13b-v1.5-q4_K_S", - "13b-v1.5-q4_K_M", - "13b-v1.5-q5_0", - "13b-v1.5-q5_1", - "13b-v1.5-q5_K_S", - "13b-v1.5-q5_K_M", - "13b-v1.5-q6_K", - "13b-v1.5-q8_0", - "13b-v1.5-fp16", - "13b-v1.6", - "13b-v1.6-vicuna-q2_K", - "13b-v1.6-vicuna-q3_K_S", - "13b-v1.6-vicuna-q3_K_M", - "13b-v1.6-vicuna-q3_K_L", - "13b-v1.6-vicuna-q4_0", - "13b-v1.6-vicuna-q4_1", - "13b-v1.6-vicuna-q4_K_S", - "13b-v1.6-vicuna-q4_K_M", - "13b-v1.6-vicuna-q5_0", - "13b-v1.6-vicuna-q5_1", - "13b-v1.6-vicuna-q5_K_S", - "13b-v1.6-vicuna-q5_K_M", - "13b-v1.6-vicuna-q6_K", - "13b-v1.6-vicuna-q8_0", - "13b-v1.6-vicuna-fp16", - "34b-v1.6", - "34b-v1.6-q2_K", - "34b-v1.6-q3_K_S", - "34b-v1.6-q3_K_M", - "34b-v1.6-q3_K_L", - "34b-v1.6-q4_0", - "34b-v1.6-q4_1", - "34b-v1.6-q4_K_S", - "34b-v1.6-q4_K_M", - "34b-v1.6-q5_0", - "34b-v1.6-q5_1", - "34b-v1.6-q5_K_S", - "34b-v1.6-q5_K_M", - "34b-v1.6-q6_K", - "34b-v1.6-q8_0", - "34b-v1.6-fp16" - ], - "qwen2.5-coder": [ - "latest", - "0.5b", - "1.5b", - "3b", - "7b", - "14b", - "32b", - "0.5b-base", - "0.5b-base-q2_K", - "0.5b-base-q3_K_S", - "0.5b-base-q3_K_M", - "0.5b-base-q3_K_L", - "0.5b-base-q4_0", - "0.5b-base-q4_1", - "0.5b-base-q4_K_S", - "0.5b-base-q4_K_M", - "0.5b-base-q5_0", - "0.5b-base-q5_1", - "0.5b-base-q5_K_S", - "0.5b-base-q5_K_M", - "0.5b-base-q6_K", - "0.5b-base-q8_0", - "0.5b-base-fp16", - "0.5b-instruct", - "0.5b-instruct-q2_K", - "0.5b-instruct-q3_K_S", - "0.5b-instruct-q3_K_M", - "0.5b-instruct-q3_K_L", - "0.5b-instruct-q4_0", - "0.5b-instruct-q4_1", - "0.5b-instruct-q4_K_S", - "0.5b-instruct-q4_K_M", - "0.5b-instruct-q5_0", - "0.5b-instruct-q5_1", - "0.5b-instruct-q5_K_S", - "0.5b-instruct-q5_K_M", - "0.5b-instruct-q6_K", - "0.5b-instruct-q8_0", - "0.5b-instruct-fp16", - "1.5b-base", - "1.5b-base-q2_K", - "1.5b-base-q3_K_S", - "1.5b-base-q3_K_M", - "1.5b-base-q3_K_L", - "1.5b-base-q4_0", - "1.5b-base-q4_1", - "1.5b-base-q4_K_S", - "1.5b-base-q4_K_M", - "1.5b-base-q5_0", - "1.5b-base-q5_1", - "1.5b-base-q5_K_S", - "1.5b-base-q5_K_M", - "1.5b-base-q6_K", - "1.5b-base-q8_0", - "1.5b-base-fp16", - "1.5b-instruct", - "1.5b-instruct-q2_K", - "1.5b-instruct-q3_K_S", - "1.5b-instruct-q3_K_M", - "1.5b-instruct-q3_K_L", - "1.5b-instruct-q4_0", - "1.5b-instruct-q4_1", - "1.5b-instruct-q4_K_S", - "1.5b-instruct-q4_K_M", - "1.5b-instruct-q5_0", - "1.5b-instruct-q5_1", - "1.5b-instruct-q5_K_S", - "1.5b-instruct-q5_K_M", - "1.5b-instruct-q6_K", - "1.5b-instruct-q8_0", - "1.5b-instruct-fp16", - "3b-base", - "3b-base-q2_K", - "3b-base-q3_K_S", - "3b-base-q3_K_M", - "3b-base-q3_K_L", - "3b-base-q4_0", - "3b-base-q4_1", - "3b-base-q4_K_S", - "3b-base-q4_K_M", - "3b-base-q5_0", - "3b-base-q5_1", - "3b-base-q5_K_S", - "3b-base-q5_K_M", - "3b-base-q6_K", - "3b-base-q8_0", - "3b-base-fp16", - "3b-instruct", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16", - "7b-base", - "7b-base-q2_K", - "7b-base-q3_K_S", - "7b-base-q3_K_M", - "7b-base-q3_K_L", - "7b-base-q4_0", - "7b-base-q4_1", - "7b-base-q4_K_S", - "7b-base-q4_K_M", - "7b-base-q5_0", - "7b-base-q5_1", - "7b-base-q5_K_S", - "7b-base-q5_K_M", - "7b-base-q6_K", - "7b-base-q8_0", - "7b-base-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "14b-base", - "14b-base-q2_K", - "14b-base-q3_K_S", - "14b-base-q3_K_M", - "14b-base-q3_K_L", - "14b-base-q4_0", - "14b-base-q4_1", - "14b-base-q4_K_S", - "14b-base-q4_K_M", - "14b-base-q5_0", - "14b-base-q5_1", - "14b-base-q5_K_S", - "14b-base-q5_K_M", - "14b-base-q6_K", - "14b-base-q8_0", - "14b-base-fp16", - "14b-instruct", - "14b-instruct-q2_K", - "14b-instruct-q3_K_S", - "14b-instruct-q3_K_M", - "14b-instruct-q3_K_L", - "14b-instruct-q4_0", - "14b-instruct-q4_1", - "14b-instruct-q4_K_S", - "14b-instruct-q4_K_M", - "14b-instruct-q5_0", - "14b-instruct-q5_1", - "14b-instruct-q5_K_S", - "14b-instruct-q5_K_M", - "14b-instruct-q6_K", - "14b-instruct-q8_0", - "14b-instruct-fp16", - "32b-base", - "32b-base-q2_K", - "32b-base-q3_K_S", - "32b-base-q3_K_M", - "32b-base-q3_K_L", - "32b-base-q4_0", - "32b-base-q4_1", - "32b-base-q4_K_S", - "32b-base-q4_K_M", - "32b-base-q5_0", - "32b-base-q5_1", - "32b-base-q5_K_S", - "32b-base-q5_K_M", - "32b-base-q6_K", - "32b-base-q8_0", - "32b-base-fp16", - "32b-instruct", - "32b-instruct-q2_K", - "32b-instruct-q3_K_S", - "32b-instruct-q3_K_M", - "32b-instruct-q3_K_L", - "32b-instruct-q4_0", - "32b-instruct-q4_1", - "32b-instruct-q4_K_S", - "32b-instruct-q4_K_M", - "32b-instruct-q5_0", - "32b-instruct-q5_1", - "32b-instruct-q5_K_S", - "32b-instruct-q5_K_M", - "32b-instruct-q6_K", - "32b-instruct-q8_0", - "32b-instruct-fp16" - ], - "phi4": [ - "latest", - "14b", - "14b-q4_K_M", - "14b-q8_0", - "14b-fp16" - ], - "mxbai-embed-large": [ - "latest", - "v1", - "335m", - "335m-v1-fp16" - ], - "gemma": [ - "latest", - "instruct", - "text", - "v1.1", - "2b", - "7b", - "2b-instruct", - "2b-instruct-q2_K", - "2b-instruct-v1.1-q2_K", - "2b-instruct-q3_K_S", - "2b-instruct-v1.1-q3_K_S", - "2b-instruct-q3_K_M", - "2b-instruct-v1.1-q3_K_M", - "2b-instruct-q3_K_L", - "2b-instruct-v1.1-q3_K_L", - "2b-instruct-q4_0", - "2b-instruct-v1.1-q4_0", - "2b-instruct-q4_1", - "2b-instruct-v1.1-q4_1", - "2b-instruct-q4_K_S", - "2b-instruct-v1.1-q4_K_S", - "2b-instruct-q4_K_M", - "2b-instruct-v1.1-q4_K_M", - "2b-instruct-q5_0", - "2b-instruct-v1.1-q5_0", - "2b-instruct-q5_1", - "2b-instruct-v1.1-q5_1", - "2b-instruct-q5_K_S", - "2b-instruct-v1.1-q5_K_S", - "2b-instruct-q5_K_M", - "2b-instruct-v1.1-q5_K_M", - "2b-instruct-q6_K", - "2b-instruct-v1.1-q6_K", - "2b-instruct-q8_0", - "2b-instruct-v1.1-q8_0", - "2b-instruct-fp16", - "2b-instruct-v1.1-fp16", - "2b-text", - "2b-text-q2_K", - "2b-text-q3_K_S", - "2b-text-q3_K_M", - "2b-text-q3_K_L", - "2b-text-q4_0", - "2b-text-q4_1", - "2b-text-q4_K_S", - "2b-text-q4_K_M", - "2b-text-q5_0", - "2b-text-q5_1", - "2b-text-q5_K_S", - "2b-text-q5_K_M", - "2b-text-q6_K", - "2b-text-q8_0", - "2b-text-fp16", - "2b-v1.1", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-v1.1-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-v1.1-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-v1.1-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-v1.1-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-v1.1-q4_0", - "7b-instruct-q4_1", - "7b-instruct-v1.1-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-v1.1-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-v1.1-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-v1.1-q5_0", - "7b-instruct-q5_1", - "7b-instruct-v1.1-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-v1.1-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-v1.1-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-v1.1-q6_K", - "7b-instruct-q8_0", - "7b-instruct-v1.1-q8_0", - "7b-instruct-fp16", - "7b-instruct-v1.1-fp16", - "7b-text", - "7b-text-q2_K", - "7b-text-q3_K_S", - "7b-text-q3_K_M", - "7b-text-q3_K_L", - "7b-text-q4_0", - "7b-text-q4_1", - "7b-text-q4_K_S", - "7b-text-q4_K_M", - "7b-text-q5_0", - "7b-text-q5_1", - "7b-text-q5_K_S", - "7b-text-q5_K_M", - "7b-text-q6_K", - "7b-text-q8_0", - "7b-text-fp16", - "7b-v1.1" - ], - "qwen": [ - "latest", - "0.5b", - "1.8b", - "4b", - "7b", - "14b", - "32b", - "72b", - "110b", - "0.5b-chat", - "0.5b-chat-v1.5-q2_K", - "0.5b-chat-v1.5-q3_K_S", - "0.5b-chat-v1.5-q3_K_M", - "0.5b-chat-v1.5-q3_K_L", - "0.5b-chat-v1.5-q4_0", - "0.5b-chat-v1.5-q4_1", - "0.5b-chat-v1.5-q4_K_S", - "0.5b-chat-v1.5-q4_K_M", - "0.5b-chat-v1.5-q5_0", - "0.5b-chat-v1.5-q5_1", - "0.5b-chat-v1.5-q5_K_S", - "0.5b-chat-v1.5-q5_K_M", - "0.5b-chat-v1.5-q6_K", - "0.5b-chat-v1.5-q8_0", - "0.5b-chat-v1.5-fp16", - "0.5b-text", - "0.5b-text-v1.5-q2_K", - "0.5b-text-v1.5-q3_K_S", - "0.5b-text-v1.5-q3_K_M", - "0.5b-text-v1.5-q3_K_L", - "0.5b-text-v1.5-q4_0", - "0.5b-text-v1.5-q4_1", - "0.5b-text-v1.5-q4_K_S", - "0.5b-text-v1.5-q4_K_M", - "0.5b-text-v1.5-q5_0", - "0.5b-text-v1.5-q5_1", - "0.5b-text-v1.5-q5_K_S", - "0.5b-text-v1.5-q5_K_M", - "0.5b-text-v1.5-q6_K", - "0.5b-text-v1.5-q8_0", - "0.5b-text-v1.5-fp16", - "1.8b-chat", - "1.8b-chat-q2_K", - "1.8b-chat-v1.5-q2_K", - "1.8b-chat-q3_K_S", - "1.8b-chat-v1.5-q3_K_S", - "1.8b-chat-q3_K_M", - "1.8b-chat-v1.5-q3_K_M", - "1.8b-chat-q3_K_L", - "1.8b-chat-v1.5-q3_K_L", - "1.8b-chat-q4_0", - "1.8b-chat-v1.5-q4_0", - "1.8b-chat-q4_1", - "1.8b-chat-v1.5-q4_1", - "1.8b-chat-q4_K_S", - "1.8b-chat-v1.5-q4_K_S", - "1.8b-chat-q4_K_M", - "1.8b-chat-v1.5-q4_K_M", - "1.8b-chat-q5_0", - "1.8b-chat-v1.5-q5_0", - "1.8b-chat-q5_1", - "1.8b-chat-v1.5-q5_1", - "1.8b-chat-q5_K_S", - "1.8b-chat-v1.5-q5_K_S", - "1.8b-chat-q5_K_M", - "1.8b-chat-v1.5-q5_K_M", - "1.8b-chat-q6_K", - "1.8b-chat-v1.5-q6_K", - "1.8b-chat-q8_0", - "1.8b-chat-v1.5-q8_0", - "1.8b-chat-fp16", - "1.8b-chat-v1.5-fp16", - "1.8b-text", - "1.8b-text-q2_K", - "1.8b-text-v1.5-q2_K", - "1.8b-text-q3_K_S", - "1.8b-text-v1.5-q3_K_S", - "1.8b-text-q3_K_M", - "1.8b-text-v1.5-q3_K_M", - "1.8b-text-q3_K_L", - "1.8b-text-v1.5-q3_K_L", - "1.8b-text-q4_0", - "1.8b-text-v1.5-q4_0", - "1.8b-text-q4_1", - "1.8b-text-v1.5-q4_1", - "1.8b-text-q4_K_S", - "1.8b-text-v1.5-q4_K_S", - "1.8b-text-q4_K_M", - "1.8b-text-v1.5-q4_K_M", - "1.8b-text-q5_0", - "1.8b-text-v1.5-q5_0", - "1.8b-text-q5_1", - "1.8b-text-v1.5-q5_1", - "1.8b-text-q5_K_S", - "1.8b-text-v1.5-q5_K_S", - "1.8b-text-q5_K_M", - "1.8b-text-v1.5-q5_K_M", - "1.8b-text-q6_K", - "1.8b-text-v1.5-q6_K", - "1.8b-text-q8_0", - "1.8b-text-v1.5-q8_0", - "1.8b-text-fp16", - "1.8b-text-v1.5-fp16", - "4b-chat", - "4b-chat-v1.5-q2_K", - "4b-chat-v1.5-q3_K_S", - "4b-chat-v1.5-q3_K_M", - "4b-chat-v1.5-q3_K_L", - "4b-chat-v1.5-q4_0", - "4b-chat-v1.5-q4_1", - "4b-chat-v1.5-q4_K_S", - "4b-chat-v1.5-q4_K_M", - "4b-chat-v1.5-q5_0", - "4b-chat-v1.5-q5_1", - "4b-chat-v1.5-q5_K_S", - "4b-chat-v1.5-q5_K_M", - "4b-chat-v1.5-q6_K", - "4b-chat-v1.5-q8_0", - "4b-chat-v1.5-fp16", - "4b-text", - "4b-text-v1.5-q2_K", - "4b-text-v1.5-q3_K_S", - "4b-text-v1.5-q3_K_M", - "4b-text-v1.5-q3_K_L", - "4b-text-v1.5-q4_0", - "4b-text-v1.5-q4_1", - "4b-text-v1.5-q4_K_S", - "4b-text-v1.5-q4_K_M", - "4b-text-v1.5-q5_0", - "4b-text-v1.5-q5_1", - "4b-text-v1.5-q5_K_S", - "4b-text-v1.5-q5_K_M", - "4b-text-v1.5-q6_K", - "4b-text-v1.5-q8_0", - "4b-text-v1.5-fp16", - "7b-chat", - "7b-chat-q2_K", - "7b-chat-v1.5-q2_K", - "7b-chat-q3_K_S", - "7b-chat-v1.5-q3_K_S", - "7b-chat-q3_K_M", - "7b-chat-v1.5-q3_K_M", - "7b-chat-q3_K_L", - "7b-chat-v1.5-q3_K_L", - "7b-chat-q4_0", - "7b-chat-v1.5-q4_0", - "7b-chat-q4_1", - "7b-chat-v1.5-q4_1", - "7b-chat-q4_K_S", - "7b-chat-v1.5-q4_K_S", - "7b-chat-q4_K_M", - "7b-chat-v1.5-q4_K_M", - "7b-chat-q5_0", - "7b-chat-v1.5-q5_0", - "7b-chat-q5_1", - "7b-chat-v1.5-q5_1", - "7b-chat-q5_K_S", - "7b-chat-v1.5-q5_K_S", - "7b-chat-q5_K_M", - "7b-chat-v1.5-q5_K_M", - "7b-chat-q6_K", - "7b-chat-v1.5-q6_K", - "7b-chat-q8_0", - "7b-chat-v1.5-q8_0", - "7b-chat-fp16", - "7b-chat-v1.5-fp16", - "7b-text", - "7b-text-v1.5-q2_K", - "7b-text-v1.5-q3_K_S", - "7b-text-v1.5-q3_K_M", - "7b-text-v1.5-q3_K_L", - "7b-text-v1.5-q4_0", - "7b-text-v1.5-q4_1", - "7b-text-v1.5-q4_K_S", - "7b-text-v1.5-q4_K_M", - "7b-text-v1.5-q5_0", - "7b-text-v1.5-q5_1", - "7b-text-v1.5-q5_K_S", - "7b-text-v1.5-q5_K_M", - "7b-text-v1.5-q6_K", - "7b-text-v1.5-q8_0", - "7b-text-v1.5-fp16", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "14b-chat", - "14b-chat-q2_K", - "14b-chat-v1.5-q2_K", - "14b-chat-q3_K_S", - "14b-chat-v1.5-q3_K_S", - "14b-chat-q3_K_M", - "14b-chat-v1.5-q3_K_M", - "14b-chat-q3_K_L", - "14b-chat-v1.5-q3_K_L", - "14b-chat-q4_0", - "14b-chat-v1.5-q4_0", - "14b-chat-q4_1", - "14b-chat-v1.5-q4_1", - "14b-chat-q4_K_S", - "14b-chat-v1.5-q4_K_S", - "14b-chat-q4_K_M", - "14b-chat-v1.5-q4_K_M", - "14b-chat-q5_0", - "14b-chat-v1.5-q5_0", - "14b-chat-q5_1", - "14b-chat-v1.5-q5_1", - "14b-chat-q5_K_S", - "14b-chat-v1.5-q5_K_S", - "14b-chat-q5_K_M", - "14b-chat-v1.5-q5_K_M", - "14b-chat-q6_K", - "14b-chat-v1.5-q6_K", - "14b-chat-q8_0", - "14b-chat-v1.5-q8_0", - "14b-chat-fp16", - "14b-chat-v1.5-fp16", - "14b-text", - "14b-text-q2_K", - "14b-text-v1.5-q2_K", - "14b-text-q3_K_S", - "14b-text-v1.5-q3_K_S", - "14b-text-q3_K_M", - "14b-text-v1.5-q3_K_M", - "14b-text-q3_K_L", - "14b-text-v1.5-q3_K_L", - "14b-text-q4_0", - "14b-text-v1.5-q4_0", - "14b-text-q4_1", - "14b-text-v1.5-q4_1", - "14b-text-q4_K_S", - "14b-text-v1.5-q4_K_S", - "14b-text-q4_K_M", - "14b-text-v1.5-q4_K_M", - "14b-text-q5_0", - "14b-text-v1.5-q5_0", - "14b-text-q5_1", - "14b-text-v1.5-q5_1", - "14b-text-q5_K_S", - "14b-text-v1.5-q5_K_S", - "14b-text-q5_K_M", - "14b-text-v1.5-q5_K_M", - "14b-text-q6_K", - "14b-text-v1.5-q6_K", - "14b-text-q8_0", - "14b-text-v1.5-q8_0", - "14b-text-fp16", - "14b-text-v1.5-fp16", - "32b-chat", - "32b-chat-v1.5-q2_K", - "32b-chat-v1.5-q3_K_S", - "32b-chat-v1.5-q3_K_M", - "32b-chat-v1.5-q3_K_L", - "32b-chat-v1.5-q4_0", - "32b-chat-v1.5-q4_1", - "32b-chat-v1.5-q4_K_S", - "32b-chat-v1.5-q4_K_M", - "32b-chat-v1.5-q5_0", - "32b-chat-v1.5-q5_1", - "32b-chat-v1.5-q5_K_S", - "32b-chat-v1.5-q5_K_M", - "32b-chat-v1.5-q6_K", - "32b-chat-v1.5-q8_0", - "32b-chat-v1.5-fp16", - "32b-text", - "32b-text-v1.5-q2_K", - "32b-text-v1.5-q3_K_S", - "32b-text-v1.5-q3_K_M", - "32b-text-v1.5-q3_K_L", - "32b-text-v1.5-q4_0", - "32b-text-v1.5-q4_1", - "32b-text-v1.5-q4_K_S", - "32b-text-v1.5-q5_0", - "32b-text-v1.5-q5_1", - "32b-text-v1.5-q8_0", - "72b-chat", - "72b-chat-q2_K", - "72b-chat-v1.5-q2_K", - "72b-chat-q3_K_S", - "72b-chat-v1.5-q3_K_S", - "72b-chat-q3_K_M", - "72b-chat-v1.5-q3_K_M", - "72b-chat-q3_K_L", - "72b-chat-v1.5-q3_K_L", - "72b-chat-q4_0", - "72b-chat-v1.5-q4_0", - "72b-chat-q4_1", - "72b-chat-v1.5-q4_1", - "72b-chat-q4_K_S", - "72b-chat-v1.5-q4_K_S", - "72b-chat-q4_K_M", - "72b-chat-v1.5-q4_K_M", - "72b-chat-q5_0", - "72b-chat-v1.5-q5_0", - "72b-chat-q5_1", - "72b-chat-v1.5-q5_1", - "72b-chat-q5_K_S", - "72b-chat-v1.5-q5_K_S", - "72b-chat-q5_K_M", - "72b-chat-v1.5-q5_K_M", - "72b-chat-q6_K", - "72b-chat-v1.5-q6_K", - "72b-chat-q8_0", - "72b-chat-v1.5-q8_0", - "72b-chat-fp16", - "72b-chat-v1.5-fp16", - "72b-text", - "72b-text-q2_K", - "72b-text-v1.5-q2_K", - "72b-text-q3_K_S", - "72b-text-v1.5-q3_K_S", - "72b-text-q3_K_M", - "72b-text-v1.5-q3_K_M", - "72b-text-q3_K_L", - "72b-text-v1.5-q3_K_L", - "72b-text-q4_0", - "72b-text-v1.5-q4_0", - "72b-text-q4_1", - "72b-text-v1.5-q4_1", - "72b-text-q4_K_S", - "72b-text-v1.5-q4_K_S", - "72b-text-q4_K_M", - "72b-text-v1.5-q4_K_M", - "72b-text-q5_0", - "72b-text-v1.5-q5_0", - "72b-text-q5_1", - "72b-text-v1.5-q5_1", - "72b-text-q5_K_S", - "72b-text-v1.5-q5_K_S", - "72b-text-q5_K_M", - "72b-text-v1.5-q5_K_M", - "72b-text-q6_K", - "72b-text-v1.5-q6_K", - "72b-text-q8_0", - "72b-text-v1.5-q8_0", - "72b-text-fp16", - "72b-text-v1.5-fp16", - "110b-chat", - "110b-chat-v1.5-q2_K", - "110b-chat-v1.5-q3_K_S", - "110b-chat-v1.5-q3_K_M", - "110b-chat-v1.5-q3_K_L", - "110b-chat-v1.5-q4_0", - "110b-chat-v1.5-q4_1", - "110b-chat-v1.5-q4_K_S", - "110b-chat-v1.5-q4_K_M", - "110b-chat-v1.5-q5_0", - "110b-chat-v1.5-q5_1", - "110b-chat-v1.5-q5_K_S", - "110b-chat-v1.5-q5_K_M", - "110b-chat-v1.5-q6_K", - "110b-chat-v1.5-q8_0", - "110b-chat-v1.5-fp16", - "110b-text-v1.5-q2_K", - "110b-text-v1.5-q3_K_S", - "110b-text-v1.5-q3_K_M", - "110b-text-v1.5-q3_K_L", - "110b-text-v1.5-q4_0", - "110b-text-v1.5-q4_1", - "110b-text-v1.5-q4_K_S", - "110b-text-v1.5-q4_K_M", - "110b-text-v1.5-q5_0", - "110b-text-v1.5-q5_1", - "110b-text-v1.5-q5_K_S", - "110b-text-v1.5-q5_K_M", - "110b-text-v1.5-q6_K", - "110b-text-v1.5-q8_0", - "110b-text-v1.5-fp16" - ], - "llama2": [ - "latest", - "chat", - "text", - "7b", - "13b", - "70b", - "7b-chat", - "7b-chat-q2_K", - "7b-chat-q3_K_S", - "7b-chat-q3_K_M", - "7b-chat-q3_K_L", - "7b-chat-q4_0", - "7b-chat-q4_1", - "7b-chat-q4_K_S", - "7b-chat-q4_K_M", - "7b-chat-q5_0", - "7b-chat-q5_1", - "7b-chat-q5_K_S", - "7b-chat-q5_K_M", - "7b-chat-q6_K", - "7b-chat-q8_0", - "7b-chat-fp16", - "7b-text", - "7b-text-q2_K", - "7b-text-q3_K_S", - "7b-text-q3_K_M", - "7b-text-q3_K_L", - "7b-text-q4_0", - "7b-text-q4_1", - "7b-text-q4_K_S", - "7b-text-q4_K_M", - "7b-text-q5_0", - "7b-text-q5_1", - "7b-text-q5_K_S", - "7b-text-q5_K_M", - "7b-text-q6_K", - "7b-text-q8_0", - "7b-text-fp16", - "13b-chat", - "13b-chat-q2_K", - "13b-chat-q3_K_S", - "13b-chat-q3_K_M", - "13b-chat-q3_K_L", - "13b-chat-q4_0", - "13b-chat-q4_1", - "13b-chat-q4_K_S", - "13b-chat-q4_K_M", - "13b-chat-q5_0", - "13b-chat-q5_1", - "13b-chat-q5_K_S", - "13b-chat-q5_K_M", - "13b-chat-q6_K", - "13b-chat-q8_0", - "13b-chat-fp16", - "13b-text", - "13b-text-q2_K", - "13b-text-q3_K_S", - "13b-text-q3_K_M", - "13b-text-q3_K_L", - "13b-text-q4_0", - "13b-text-q4_1", - "13b-text-q4_K_S", - "13b-text-q4_K_M", - "13b-text-q5_0", - "13b-text-q5_1", - "13b-text-q5_K_S", - "13b-text-q5_K_M", - "13b-text-q6_K", - "13b-text-q8_0", - "13b-text-fp16", - "70b-chat", - "70b-chat-q2_K", - "70b-chat-q3_K_S", - "70b-chat-q3_K_M", - "70b-chat-q3_K_L", - "70b-chat-q4_0", - "70b-chat-q4_1", - "70b-chat-q4_K_S", - "70b-chat-q4_K_M", - "70b-chat-q5_0", - "70b-chat-q5_1", - "70b-chat-q5_K_S", - "70b-chat-q5_K_M", - "70b-chat-q6_K", - "70b-chat-q8_0", - "70b-chat-fp16", - "70b-text", - "70b-text-q2_K", - "70b-text-q3_K_S", - "70b-text-q3_K_M", - "70b-text-q3_K_L", - "70b-text-q4_0", - "70b-text-q4_1", - "70b-text-q4_K_S", - "70b-text-q4_K_M", - "70b-text-q5_0", - "70b-text-q5_1", - "70b-text-q5_K_S", - "70b-text-q5_K_M", - "70b-text-q6_K", - "70b-text-q8_0", - "70b-text-fp16" - ], - "qwen2": [ - "latest", - "0.5b", - "1.5b", - "7b", - "72b", - "0.5b-instruct", - "0.5b-instruct-q2_K", - "0.5b-instruct-q3_K_S", - "0.5b-instruct-q3_K_M", - "0.5b-instruct-q3_K_L", - "0.5b-instruct-q4_0", - "0.5b-instruct-q4_1", - "0.5b-instruct-q4_K_S", - "0.5b-instruct-q4_K_M", - "0.5b-instruct-q5_0", - "0.5b-instruct-q5_1", - "0.5b-instruct-q5_K_S", - "0.5b-instruct-q5_K_M", - "0.5b-instruct-q6_K", - "0.5b-instruct-q8_0", - "0.5b-instruct-fp16", - "1.5b-instruct", - "1.5b-instruct-q2_K", - "1.5b-instruct-q3_K_S", - "1.5b-instruct-q3_K_M", - "1.5b-instruct-q3_K_L", - "1.5b-instruct-q4_0", - "1.5b-instruct-q4_1", - "1.5b-instruct-q4_K_S", - "1.5b-instruct-q4_K_M", - "1.5b-instruct-q5_0", - "1.5b-instruct-q5_1", - "1.5b-instruct-q5_K_S", - "1.5b-instruct-q5_K_M", - "1.5b-instruct-q6_K", - "1.5b-instruct-q8_0", - "1.5b-instruct-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "7b-text", - "7b-text-q2_K", - "7b-text-q3_K_S", - "7b-text-q3_K_M", - "7b-text-q3_K_L", - "7b-text-q4_0", - "7b-text-q4_1", - "7b-text-q4_K_S", - "7b-text-q4_K_M", - "7b-text-q5_0", - "7b-text-q5_1", - "7b-text-q8_0", - "72b-instruct", - "72b-instruct-q2_K", - "72b-instruct-q3_K_S", - "72b-instruct-q3_K_M", - "72b-instruct-q3_K_L", - "72b-instruct-q4_0", - "72b-instruct-q4_1", - "72b-instruct-q4_K_S", - "72b-instruct-q4_K_M", - "72b-instruct-q5_0", - "72b-instruct-q5_1", - "72b-instruct-q5_K_S", - "72b-instruct-q5_K_M", - "72b-instruct-q6_K", - "72b-instruct-q8_0", - "72b-instruct-fp16", - "72b-text", - "72b-text-q2_K", - "72b-text-q3_K_S", - "72b-text-q3_K_M", - "72b-text-q3_K_L", - "72b-text-q4_0", - "72b-text-q4_1", - "72b-text-q4_K_S", - "72b-text-q4_K_M", - "72b-text-q5_0", - "72b-text-q5_1", - "72b-text-q5_K_S", - "72b-text-q5_K_M", - "72b-text-q6_K", - "72b-text-q8_0", - "72b-text-fp16" - ], - "minicpm-v": [ - "latest", - "8b", - "8b-2.6-q2_K", - "8b-2.6-q3_K_S", - "8b-2.6-q3_K_M", - "8b-2.6-q3_K_L", - "8b-2.6-q4_0", - "8b-2.6-q4_1", - "8b-2.6-q4_K_S", - "8b-2.6-q4_K_M", - "8b-2.6-q5_0", - "8b-2.6-q5_1", - "8b-2.6-q5_K_S", - "8b-2.6-q5_K_M", - "8b-2.6-q6_K", - "8b-2.6-q8_0", - "8b-2.6-fp16" - ], - "codellama": [ - "latest", - "code", - "instruct", - "python", - "7b", - "13b", - "34b", - "70b", - "7b-code", - "7b-code-q2_K", - "7b-code-q3_K_S", - "7b-code-q3_K_M", - "7b-code-q3_K_L", - "7b-code-q4_0", - "7b-code-q4_1", - "7b-code-q4_K_S", - "7b-code-q4_K_M", - "7b-code-q5_0", - "7b-code-q5_1", - "7b-code-q5_K_S", - "7b-code-q5_K_M", - "7b-code-q6_K", - "7b-code-q8_0", - "7b-code-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "7b-python", - "7b-python-q2_K", - "7b-python-q3_K_S", - "7b-python-q3_K_M", - "7b-python-q3_K_L", - "7b-python-q4_0", - "7b-python-q4_1", - "7b-python-q4_K_S", - "7b-python-q4_K_M", - "7b-python-q5_0", - "7b-python-q5_1", - "7b-python-q5_K_S", - "7b-python-q5_K_M", - "7b-python-q6_K", - "7b-python-q8_0", - "7b-python-fp16", - "13b-code", - "13b-code-q2_K", - "13b-code-q3_K_S", - "13b-code-q3_K_M", - "13b-code-q3_K_L", - "13b-code-q4_0", - "13b-code-q4_1", - "13b-code-q4_K_S", - "13b-code-q4_K_M", - "13b-code-q5_0", - "13b-code-q5_1", - "13b-code-q5_K_S", - "13b-code-q5_K_M", - "13b-code-q6_K", - "13b-code-q8_0", - "13b-code-fp16", - "13b-instruct", - "13b-instruct-q2_K", - "13b-instruct-q3_K_S", - "13b-instruct-q3_K_M", - "13b-instruct-q3_K_L", - "13b-instruct-q4_0", - "13b-instruct-q4_1", - "13b-instruct-q4_K_S", - "13b-instruct-q4_K_M", - "13b-instruct-q5_0", - "13b-instruct-q5_1", - "13b-instruct-q5_K_S", - "13b-instruct-q5_K_M", - "13b-instruct-q6_K", - "13b-instruct-q8_0", - "13b-instruct-fp16", - "13b-python", - "13b-python-q2_K", - "13b-python-q3_K_S", - "13b-python-q3_K_M", - "13b-python-q3_K_L", - "13b-python-q4_0", - "13b-python-q4_1", - "13b-python-q4_K_S", - "13b-python-q4_K_M", - "13b-python-q5_0", - "13b-python-q5_1", - "13b-python-q5_K_S", - "13b-python-q5_K_M", - "13b-python-q6_K", - "13b-python-q8_0", - "13b-python-fp16", - "34b-code", - "34b-code-q2_K", - "34b-code-q3_K_S", - "34b-code-q3_K_M", - "34b-code-q3_K_L", - "34b-code-q4_0", - "34b-code-q4_1", - "34b-code-q4_K_S", - "34b-code-q4_K_M", - "34b-code-q5_0", - "34b-code-q5_1", - "34b-code-q5_K_S", - "34b-code-q5_K_M", - "34b-code-q6_K", - "34b-code-q8_0", - "34b-instruct", - "34b-instruct-q2_K", - "34b-instruct-q3_K_S", - "34b-instruct-q3_K_M", - "34b-instruct-q3_K_L", - "34b-instruct-q4_0", - "34b-instruct-q4_1", - "34b-instruct-q4_K_S", - "34b-instruct-q4_K_M", - "34b-instruct-q5_0", - "34b-instruct-q5_1", - "34b-instruct-q5_K_S", - "34b-instruct-q5_K_M", - "34b-instruct-q6_K", - "34b-instruct-q8_0", - "34b-instruct-fp16", - "34b-python", - "34b-python-q2_K", - "34b-python-q3_K_S", - "34b-python-q3_K_M", - "34b-python-q3_K_L", - "34b-python-q4_0", - "34b-python-q4_1", - "34b-python-q4_K_S", - "34b-python-q4_K_M", - "34b-python-q5_0", - "34b-python-q5_1", - "34b-python-q5_K_S", - "34b-python-q5_K_M", - "34b-python-q6_K", - "34b-python-q8_0", - "34b-python-fp16", - "70b-code", - "70b-code-q2_K", - "70b-code-q3_K_S", - "70b-code-q3_K_M", - "70b-code-q3_K_L", - "70b-code-q4_0", - "70b-code-q4_1", - "70b-code-q4_K_S", - "70b-code-q4_K_M", - "70b-code-q5_0", - "70b-code-q5_1", - "70b-code-q5_K_S", - "70b-code-q5_K_M", - "70b-code-q6_K", - "70b-code-q8_0", - "70b-code-fp16", - "70b-instruct", - "70b-instruct-q2_K", - "70b-instruct-q3_K_S", - "70b-instruct-q3_K_M", - "70b-instruct-q3_K_L", - "70b-instruct-q4_0", - "70b-instruct-q4_1", - "70b-instruct-q4_K_S", - "70b-instruct-q4_K_M", - "70b-instruct-q5_0", - "70b-instruct-q5_1", - "70b-instruct-q5_K_S", - "70b-instruct-q5_K_M", - "70b-instruct-q6_K", - "70b-instruct-q8_0", - "70b-instruct-fp16", - "70b-python", - "70b-python-q2_K", - "70b-python-q3_K_S", - "70b-python-q3_K_M", - "70b-python-q3_K_L", - "70b-python-q4_0", - "70b-python-q4_1", - "70b-python-q4_K_S", - "70b-python-q4_K_M", - "70b-python-q5_0", - "70b-python-q5_1", - "70b-python-q5_K_S", - "70b-python-q5_K_M", - "70b-python-q6_K", - "70b-python-q8_0", - "70b-python-fp16" - ], - "llama3.2-vision": [ - "latest", - "11b", - "90b", - "11b-instruct-q4_K_M", - "11b-instruct-q8_0", - "11b-instruct-fp16", - "90b-instruct-q4_K_M", - "90b-instruct-q8_0", - "90b-instruct-fp16" - ], - "dolphin3": [ - "latest", - "8b", - "8b-llama3.1-q4_K_M", - "8b-llama3.1-q8_0", - "8b-llama3.1-fp16" - ], - "olmo2": [ - "latest", - "7b", - "13b", - "7b-1124-instruct-q4_K_M", - "7b-1124-instruct-q8_0", - "7b-1124-instruct-fp16", - "13b-1124-instruct-q4_K_M", - "13b-1124-instruct-q8_0", - "13b-1124-instruct-fp16" - ], - "tinyllama": [ - "latest", - "chat", - "v0.6", - "v1", - "1.1b", - "1.1b-chat", - "1.1b-chat-v0.6-q2_K", - "1.1b-chat-v0.6-q3_K_S", - "1.1b-chat-v0.6-q3_K_M", - "1.1b-chat-v0.6-q3_K_L", - "1.1b-chat-v0.6-q4_0", - "1.1b-chat-v0.6-q4_1", - "1.1b-chat-v0.6-q4_K_S", - "1.1b-chat-v0.6-q4_K_M", - "1.1b-chat-v0.6-q5_0", - "1.1b-chat-v0.6-q5_1", - "1.1b-chat-v0.6-q5_K_S", - "1.1b-chat-v0.6-q5_K_M", - "1.1b-chat-v0.6-q6_K", - "1.1b-chat-v0.6-q8_0", - "1.1b-chat-v0.6-fp16", - "1.1b-chat-v1-q2_K", - "1.1b-chat-v1-q3_K_S", - "1.1b-chat-v1-q3_K_M", - "1.1b-chat-v1-q3_K_L", - "1.1b-chat-v1-q4_0", - "1.1b-chat-v1-q4_1", - "1.1b-chat-v1-q4_K_S", - "1.1b-chat-v1-q4_K_M", - "1.1b-chat-v1-q5_0", - "1.1b-chat-v1-q5_1", - "1.1b-chat-v1-q5_K_S", - "1.1b-chat-v1-q5_K_M", - "1.1b-chat-v1-q6_K", - "1.1b-chat-v1-q8_0", - "1.1b-chat-v1-fp16" - ], - "mistral-nemo": [ - "latest", - "12b", - "12b-instruct-2407-q2_K", - "12b-instruct-2407-q3_K_S", - "12b-instruct-2407-q3_K_M", - "12b-instruct-2407-q3_K_L", - "12b-instruct-2407-q4_0", - "12b-instruct-2407-q4_1", - "12b-instruct-2407-q4_K_S", - "12b-instruct-2407-q4_K_M", - "12b-instruct-2407-q5_0", - "12b-instruct-2407-q5_1", - "12b-instruct-2407-q5_K_S", - "12b-instruct-2407-q5_K_M", - "12b-instruct-2407-q6_K", - "12b-instruct-2407-q8_0", - "12b-instruct-2407-fp16" - ], - "deepseek-v3": [ - "latest", - "671b", - "671b-q4_K_M", - "671b-q8_0", - "671b-fp16" - ], - "bge-m3": [ - "latest", - "567m", - "567m-fp16" - ], - "llama3.3": [ - "latest", - "70b", - "70b-instruct-q2_K", - "70b-instruct-q3_K_S", - "70b-instruct-q3_K_M", - "70b-instruct-q4_0", - "70b-instruct-q4_K_S", - "70b-instruct-q4_K_M", - "70b-instruct-q5_0", - "70b-instruct-q5_1", - "70b-instruct-q5_K_M", - "70b-instruct-q6_K", - "70b-instruct-q8_0", - "70b-instruct-fp16" - ], - "deepseek-coder": [ - "latest", - "base", - "instruct", - "1.3b", - "6.7b", - "33b", - "1.3b-base", - "1.3b-base-q2_K", - "1.3b-base-q3_K_S", - "1.3b-base-q3_K_M", - "1.3b-base-q3_K_L", - "1.3b-base-q4_0", - "1.3b-base-q4_1", - "1.3b-base-q4_K_S", - "1.3b-base-q4_K_M", - "1.3b-base-q5_0", - "1.3b-base-q5_1", - "1.3b-base-q5_K_S", - "1.3b-base-q5_K_M", - "1.3b-base-q6_K", - "1.3b-base-q8_0", - "1.3b-base-fp16", - "1.3b-instruct", - "1.3b-instruct-q2_K", - "1.3b-instruct-q3_K_S", - "1.3b-instruct-q3_K_M", - "1.3b-instruct-q3_K_L", - "1.3b-instruct-q4_0", - "1.3b-instruct-q4_1", - "1.3b-instruct-q4_K_S", - "1.3b-instruct-q4_K_M", - "1.3b-instruct-q5_0", - "1.3b-instruct-q5_1", - "1.3b-instruct-q5_K_S", - "1.3b-instruct-q5_K_M", - "1.3b-instruct-q6_K", - "1.3b-instruct-q8_0", - "1.3b-instruct-fp16", - "6.7b-base", - "6.7b-base-q2_K", - "6.7b-base-q3_K_S", - "6.7b-base-q3_K_M", - "6.7b-base-q3_K_L", - "6.7b-base-q4_0", - "6.7b-base-q4_1", - "6.7b-base-q4_K_S", - "6.7b-base-q4_K_M", - "6.7b-base-q5_0", - "6.7b-base-q5_1", - "6.7b-base-q5_K_S", - "6.7b-base-q5_K_M", - "6.7b-base-q6_K", - "6.7b-base-q8_0", - "6.7b-base-fp16", - "6.7b-instruct", - "6.7b-instruct-q2_K", - "6.7b-instruct-q3_K_S", - "6.7b-instruct-q3_K_M", - "6.7b-instruct-q3_K_L", - "6.7b-instruct-q4_0", - "6.7b-instruct-q4_1", - "6.7b-instruct-q4_K_S", - "6.7b-instruct-q4_K_M", - "6.7b-instruct-q5_0", - "6.7b-instruct-q5_1", - "6.7b-instruct-q5_K_S", - "6.7b-instruct-q5_K_M", - "6.7b-instruct-q6_K", - "6.7b-instruct-q8_0", - "6.7b-instruct-fp16", - "33b-base", - "33b-base-q2_K", - "33b-base-q3_K_S", - "33b-base-q3_K_M", - "33b-base-q3_K_L", - "33b-base-q4_0", - "33b-base-q4_1", - "33b-base-q4_K_S", - "33b-base-q4_K_M", - "33b-base-q5_0", - "33b-base-q5_1", - "33b-base-q5_K_S", - "33b-base-q5_K_M", - "33b-base-q6_K", - "33b-base-q8_0", - "33b-base-fp16", - "33b-instruct", - "33b-instruct-q2_K", - "33b-instruct-q3_K_S", - "33b-instruct-q3_K_M", - "33b-instruct-q3_K_L", - "33b-instruct-q4_0", - "33b-instruct-q4_1", - "33b-instruct-q4_K_S", - "33b-instruct-q4_K_M", - "33b-instruct-q5_0", - "33b-instruct-q5_1", - "33b-instruct-q5_K_S", - "33b-instruct-q5_K_M", - "33b-instruct-q6_K", - "33b-instruct-q8_0", - "33b-instruct-fp16" - ], - "smollm2": [ - "latest", - "135m", - "360m", - "1.7b", - "135m-instruct-q2_K", - "135m-instruct-q3_K_S", - "135m-instruct-q3_K_M", - "135m-instruct-q3_K_L", - "135m-instruct-q4_0", - "135m-instruct-q4_1", - "135m-instruct-q4_K_S", - "135m-instruct-q4_K_M", - "135m-instruct-q5_0", - "135m-instruct-q5_1", - "135m-instruct-q5_K_S", - "135m-instruct-q5_K_M", - "135m-instruct-q6_K", - "135m-instruct-q8_0", - "135m-instruct-fp16", - "360m-instruct-q2_K", - "360m-instruct-q3_K_S", - "360m-instruct-q3_K_M", - "360m-instruct-q3_K_L", - "360m-instruct-q4_0", - "360m-instruct-q4_1", - "360m-instruct-q4_K_S", - "360m-instruct-q4_K_M", - "360m-instruct-q5_0", - "360m-instruct-q5_1", - "360m-instruct-q5_K_S", - "360m-instruct-q5_K_M", - "360m-instruct-q6_K", - "360m-instruct-q8_0", - "360m-instruct-fp16", - "1.7b-instruct-q2_K", - "1.7b-instruct-q3_K_S", - "1.7b-instruct-q3_K_M", - "1.7b-instruct-q3_K_L", - "1.7b-instruct-q4_0", - "1.7b-instruct-q4_1", - "1.7b-instruct-q4_K_S", - "1.7b-instruct-q4_K_M", - "1.7b-instruct-q5_0", - "1.7b-instruct-q5_1", - "1.7b-instruct-q5_K_S", - "1.7b-instruct-q5_K_M", - "1.7b-instruct-q6_K", - "1.7b-instruct-q8_0", - "1.7b-instruct-fp16" - ], - "mistral-small": [ - "latest", - "22b", - "24b", - "22b-instruct-2409-q2_K", - "22b-instruct-2409-q3_K_S", - "22b-instruct-2409-q3_K_M", - "22b-instruct-2409-q3_K_L", - "22b-instruct-2409-q4_0", - "22b-instruct-2409-q4_1", - "22b-instruct-2409-q4_K_S", - "22b-instruct-2409-q4_K_M", - "22b-instruct-2409-q5_0", - "22b-instruct-2409-q5_1", - "22b-instruct-2409-q5_K_S", - "22b-instruct-2409-q5_K_M", - "22b-instruct-2409-q6_K", - "22b-instruct-2409-q8_0", - "22b-instruct-2409-fp16", - "24b-instruct-2501-q4_K_M", - "24b-instruct-2501-q8_0", - "24b-instruct-2501-fp16" - ], - "all-minilm": [ - "latest", - "l12", - "l6", - "v2", - "22m", - "33m", - "22m-l6-v2-fp16", - "33m-l12-v2-fp16", - "l12-v2", - "l6-v2" - ], - "llava-llama3": [ - "latest", - "8b", - "8b-v1.1-q4_0", - "8b-v1.1-fp16" - ], - "qwq": [ - "latest", - "32b", - "32b-preview-q4_K_M", - "32b-preview-q8_0", - "32b-preview-fp16", - "32b-q4_K_M", - "32b-q8_0", - "32b-fp16" - ], - "codegemma": [ - "latest", - "code", - "instruct", - "2b", - "7b", - "2b-code", - "2b-code-q2_K", - "2b-code-v1.1-q2_K", - "2b-code-q3_K_S", - "2b-code-v1.1-q3_K_S", - "2b-code-q3_K_M", - "2b-code-v1.1-q3_K_M", - "2b-code-q3_K_L", - "2b-code-v1.1-q3_K_L", - "2b-code-q4_0", - "2b-code-v1.1-q4_0", - "2b-code-q4_1", - "2b-code-v1.1-q4_1", - "2b-code-q4_K_S", - "2b-code-v1.1-q4_K_S", - "2b-code-q4_K_M", - "2b-code-v1.1-q4_K_M", - "2b-code-q5_0", - "2b-code-v1.1-q5_0", - "2b-code-q5_1", - "2b-code-v1.1-q5_1", - "2b-code-q5_K_S", - "2b-code-v1.1-q5_K_S", - "2b-code-q5_K_M", - "2b-code-v1.1-q5_K_M", - "2b-code-q6_K", - "2b-code-v1.1-q6_K", - "2b-code-q8_0", - "2b-code-v1.1-q8_0", - "2b-code-fp16", - "2b-code-v1.1-fp16", - "2b-v1.1", - "7b-code", - "7b-code-q2_K", - "7b-code-q3_K_S", - "7b-code-q3_K_M", - "7b-code-q3_K_L", - "7b-code-q4_0", - "7b-code-q4_1", - "7b-code-q4_K_S", - "7b-code-q4_K_M", - "7b-code-q5_0", - "7b-code-q5_1", - "7b-code-q5_K_S", - "7b-code-q5_K_M", - "7b-code-q6_K", - "7b-code-q8_0", - "7b-code-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-v1.1-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-v1.1-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-v1.1-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-v1.1-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-v1.1-q4_0", - "7b-instruct-q4_1", - "7b-instruct-v1.1-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-v1.1-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-v1.1-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-v1.1-q5_0", - "7b-instruct-q5_1", - "7b-instruct-v1.1-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-v1.1-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-v1.1-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-v1.1-q6_K", - "7b-instruct-q8_0", - "7b-instruct-v1.1-q8_0", - "7b-instruct-fp16", - "7b-instruct-v1.1-fp16", - "7b-v1.1" - ], - "granite3.1-moe": [ - "latest", - "1b", - "3b", - "1b-instruct-q2_K", - "1b-instruct-q3_K_S", - "1b-instruct-q3_K_M", - "1b-instruct-q3_K_L", - "1b-instruct-q4_0", - "1b-instruct-q4_1", - "1b-instruct-q4_K_S", - "1b-instruct-q4_K_M", - "1b-instruct-q5_0", - "1b-instruct-q5_1", - "1b-instruct-q5_K_S", - "1b-instruct-q5_K_M", - "1b-instruct-q6_K", - "1b-instruct-q8_0", - "1b-instruct-fp16", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16" - ], - "falcon3": [ - "latest", - "1b", - "3b", - "7b", - "10b", - "1b-instruct-q4_K_M", - "1b-instruct-q8_0", - "1b-instruct-fp16", - "3b-instruct-q4_K_M", - "3b-instruct-q8_0", - "3b-instruct-fp16", - "7b-instruct-q4_K_M", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "10b-instruct-q4_K_M", - "10b-instruct-q8_0", - "10b-instruct-fp16" - ], - "starcoder2": [ - "latest", - "instruct", - "3b", - "7b", - "15b", - "3b-q2_K", - "3b-q3_K_S", - "3b-q3_K_M", - "3b-q3_K_L", - "3b-q4_0", - "3b-q4_1", - "3b-q4_K_S", - "3b-q4_K_M", - "3b-q5_0", - "3b-q5_1", - "3b-q5_K_S", - "3b-q5_K_M", - "3b-q6_K", - "3b-q8_0", - "3b-fp16", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "15b-instruct", - "15b-instruct-v0.1-q2_K", - "15b-instruct-v0.1-q3_K_S", - "15b-instruct-v0.1-q3_K_M", - "15b-instruct-v0.1-q3_K_L", - "15b-instruct-q4_0", - "15b-instruct-v0.1-q4_0", - "15b-instruct-v0.1-q4_1", - "15b-instruct-v0.1-q4_K_S", - "15b-instruct-v0.1-q4_K_M", - "15b-instruct-v0.1-q5_0", - "15b-instruct-v0.1-q5_1", - "15b-instruct-v0.1-q5_K_S", - "15b-instruct-v0.1-q5_K_M", - "15b-instruct-v0.1-q6_K", - "15b-instruct-v0.1-q8_0", - "15b-instruct-v0.1-fp16", - "15b-q2_K", - "15b-q3_K_S", - "15b-q3_K_M", - "15b-q3_K_L", - "15b-q4_0", - "15b-q4_1", - "15b-q4_K_S", - "15b-q4_K_M", - "15b-q5_0", - "15b-q5_1", - "15b-q5_K_S", - "15b-q5_K_M", - "15b-q6_K", - "15b-q8_0", - "15b-fp16" - ], - "snowflake-arctic-embed": [ - "latest", - "l", - "m", - "s", - "xs", - "22m", - "33m", - "110m", - "137m", - "335m", - "22m-xs-fp16", - "33m-s-fp16", - "110m-m-fp16", - "137m-m-long-fp16", - "335m-l-fp16", - "m-long" - ], - "orca-mini": [ - "latest", - "3b", - "7b", - "13b", - "70b", - "3b-q4_0", - "3b-q4_1", - "3b-q5_0", - "3b-q5_1", - "3b-q8_0", - "3b-fp16", - "7b-v2-q2_K", - "7b-v2-q3_K_S", - "7b-v2-q3_K_M", - "7b-v2-q3_K_L", - "7b-v2-q4_0", - "7b-v2-q4_1", - "7b-v2-q4_K_S", - "7b-v2-q4_K_M", - "7b-v2-q5_0", - "7b-v2-q5_1", - "7b-v2-q5_K_S", - "7b-v2-q5_K_M", - "7b-v2-q6_K", - "7b-v2-q8_0", - "7b-v2-fp16", - "7b-v3", - "7b-v3-q2_K", - "7b-v3-q3_K_S", - "7b-v3-q3_K_M", - "7b-v3-q3_K_L", - "7b-v3-q4_0", - "7b-v3-q4_1", - "7b-v3-q4_K_S", - "7b-v3-q4_K_M", - "7b-v3-q5_0", - "7b-v3-q5_1", - "7b-v3-q5_K_S", - "7b-v3-q5_K_M", - "7b-v3-q6_K", - "7b-v3-q8_0", - "7b-v3-fp16", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-v2-q2_K", - "13b-v2-q3_K_S", - "13b-v2-q3_K_M", - "13b-v2-q3_K_L", - "13b-v2-q4_0", - "13b-v2-q4_1", - "13b-v2-q4_K_S", - "13b-v2-q4_K_M", - "13b-v2-q5_0", - "13b-v2-q5_1", - "13b-v2-q5_K_S", - "13b-v2-q5_K_M", - "13b-v2-q6_K", - "13b-v2-q8_0", - "13b-v2-fp16", - "13b-v3", - "13b-v3-q2_K", - "13b-v3-q3_K_S", - "13b-v3-q3_K_M", - "13b-v3-q3_K_L", - "13b-v3-q4_0", - "13b-v3-q4_1", - "13b-v3-q4_K_S", - "13b-v3-q4_K_M", - "13b-v3-q5_0", - "13b-v3-q5_1", - "13b-v3-q5_K_S", - "13b-v3-q5_K_M", - "13b-v3-q6_K", - "13b-v3-q8_0", - "13b-v3-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "70b-v3", - "70b-v3-q2_K", - "70b-v3-q3_K_S", - "70b-v3-q3_K_M", - "70b-v3-q3_K_L", - "70b-v3-q4_0", - "70b-v3-q4_1", - "70b-v3-q4_K_S", - "70b-v3-q4_K_M", - "70b-v3-q5_0", - "70b-v3-q5_1", - "70b-v3-q5_K_S", - "70b-v3-q5_K_M", - "70b-v3-q6_K", - "70b-v3-q8_0", - "70b-v3-fp16" - ], - "mixtral": [ - "latest", - "instruct", - "text", - "v0.1", - "8x7b", - "8x22b", - "8x7b-instruct-v0.1-q2_K", - "8x7b-instruct-v0.1-q3_K_S", - "8x7b-instruct-v0.1-q3_K_M", - "8x7b-instruct-v0.1-q3_K_L", - "8x7b-instruct-v0.1-q4_0", - "8x7b-instruct-v0.1-q4_1", - "8x7b-instruct-v0.1-q4_K_S", - "8x7b-instruct-v0.1-q4_K_M", - "8x7b-instruct-v0.1-q5_0", - "8x7b-instruct-v0.1-q5_1", - "8x7b-instruct-v0.1-q5_K_S", - "8x7b-instruct-v0.1-q5_K_M", - "8x7b-instruct-v0.1-q6_K", - "8x7b-instruct-v0.1-q8_0", - "8x7b-instruct-v0.1-fp16", - "8x7b-text", - "8x7b-text-v0.1-q2_K", - "8x7b-text-v0.1-q3_K_S", - "8x7b-text-v0.1-q3_K_M", - "8x7b-text-v0.1-q3_K_L", - "8x7b-text-v0.1-q4_0", - "8x7b-text-v0.1-q4_1", - "8x7b-text-v0.1-q4_K_S", - "8x7b-text-v0.1-q4_K_M", - "8x7b-text-v0.1-q5_0", - "8x7b-text-v0.1-q5_1", - "8x7b-text-v0.1-q5_K_S", - "8x7b-text-v0.1-q5_K_M", - "8x7b-text-v0.1-q6_K", - "8x7b-text-v0.1-q8_0", - "8x7b-text-v0.1-fp16", - "8x22b-instruct", - "8x22b-instruct-v0.1-q2_K", - "8x22b-instruct-v0.1-q3_K_S", - "8x22b-instruct-v0.1-q3_K_M", - "8x22b-instruct-v0.1-q3_K_L", - "8x22b-instruct-v0.1-q4_0", - "8x22b-instruct-v0.1-q4_1", - "8x22b-instruct-v0.1-q4_K_S", - "8x22b-instruct-v0.1-q4_K_M", - "8x22b-instruct-v0.1-q5_0", - "8x22b-instruct-v0.1-q5_1", - "8x22b-instruct-v0.1-q5_K_S", - "8x22b-instruct-v0.1-q5_K_M", - "8x22b-instruct-v0.1-q6_K", - "8x22b-instruct-v0.1-q8_0", - "8x22b-instruct-v0.1-fp16", - "8x22b-text", - "8x22b-text-v0.1-q2_K", - "8x22b-text-v0.1-q3_K_S", - "8x22b-text-v0.1-q3_K_M", - "8x22b-text-v0.1-q3_K_L", - "8x22b-text-v0.1-q4_0", - "8x22b-text-v0.1-q4_1", - "8x22b-text-v0.1-q4_K_S", - "8x22b-text-v0.1-q4_K_M", - "8x22b-text-v0.1-q5_0", - "8x22b-text-v0.1-q5_1", - "8x22b-text-v0.1-q5_K_S", - "8x22b-text-v0.1-q5_K_M", - "8x22b-text-v0.1-q6_K", - "8x22b-text-v0.1-q8_0", - "8x22b-text-v0.1-fp16", - "v0.1-instruct" - ], - "llama2-uncensored": [ - "latest", - "7b", - "70b", - "7b-chat", - "7b-chat-q2_K", - "7b-chat-q3_K_S", - "7b-chat-q3_K_M", - "7b-chat-q3_K_L", - "7b-chat-q4_0", - "7b-chat-q4_1", - "7b-chat-q4_K_S", - "7b-chat-q4_K_M", - "7b-chat-q5_0", - "7b-chat-q5_1", - "7b-chat-q5_K_S", - "7b-chat-q5_K_M", - "7b-chat-q6_K", - "7b-chat-q8_0", - "7b-chat-fp16", - "70b-chat", - "70b-chat-q2_K", - "70b-chat-q3_K_S", - "70b-chat-q3_K_M", - "70b-chat-q3_K_L", - "70b-chat-q4_0", - "70b-chat-q4_1", - "70b-chat-q4_K_S", - "70b-chat-q4_K_M", - "70b-chat-q5_0", - "70b-chat-q5_1", - "70b-chat-q5_K_S", - "70b-chat-q5_K_M", - "70b-chat-q6_K", - "70b-chat-q8_0" - ], - "deepseek-coder-v2": [ - "latest", - "lite", - "16b", - "236b", - "16b-lite-base-q2_K", - "16b-lite-base-q3_K_S", - "16b-lite-base-q3_K_M", - "16b-lite-base-q3_K_L", - "16b-lite-base-q4_0", - "16b-lite-base-q4_1", - "16b-lite-base-q4_K_S", - "16b-lite-base-q4_K_M", - "16b-lite-base-q5_0", - "16b-lite-base-q5_1", - "16b-lite-base-q5_K_S", - "16b-lite-base-q5_K_M", - "16b-lite-base-q6_K", - "16b-lite-base-q8_0", - "16b-lite-base-fp16", - "16b-lite-instruct-q2_K", - "16b-lite-instruct-q3_K_S", - "16b-lite-instruct-q3_K_M", - "16b-lite-instruct-q3_K_L", - "16b-lite-instruct-q4_0", - "16b-lite-instruct-q4_1", - "16b-lite-instruct-q4_K_S", - "16b-lite-instruct-q4_K_M", - "16b-lite-instruct-q5_0", - "16b-lite-instruct-q5_1", - "16b-lite-instruct-q5_K_S", - "16b-lite-instruct-q5_K_M", - "16b-lite-instruct-q6_K", - "16b-lite-instruct-q8_0", - "16b-lite-instruct-fp16", - "236b-base-q2_K", - "236b-base-q3_K_S", - "236b-base-q3_K_M", - "236b-base-q3_K_L", - "236b-base-q4_0", - "236b-base-q4_1", - "236b-base-q4_K_S", - "236b-base-q4_K_M", - "236b-base-q5_0", - "236b-base-q5_1", - "236b-base-q5_K_S", - "236b-base-q5_K_M", - "236b-base-q6_K", - "236b-base-q8_0", - "236b-base-fp16", - "236b-instruct-q2_K", - "236b-instruct-q3_K_S", - "236b-instruct-q3_K_M", - "236b-instruct-q3_K_L", - "236b-instruct-q4_0", - "236b-instruct-q4_1", - "236b-instruct-q4_K_S", - "236b-instruct-q4_K_M", - "236b-instruct-q5_0", - "236b-instruct-q5_1", - "236b-instruct-q5_K_S", - "236b-instruct-q5_K_M", - "236b-instruct-q6_K", - "236b-instruct-q8_0", - "236b-instruct-fp16" - ], - "cogito": [ - "latest", - "3b", - "8b", - "14b", - "32b", - "70b", - "3b-v1-preview-llama-q4_K_M", - "3b-v1-preview-llama-q8_0", - "3b-v1-preview-llama-fp16", - "8b-v1-preview-llama-q4_K_M", - "8b-v1-preview-llama-q8_0", - "14b-v1-preview-qwen-q4_K_M", - "14b-v1-preview-qwen-q8_0", - "14b-v1-preview-qwen-fp16", - "32b-v1-preview-qwen-q4_K_M", - "32b-v1-preview-qwen-q8_0", - "32b-v1-preview-qwen-fp16", - "70b-v1-preview-llama-q4_K_M", - "70b-v1-preview-llama-q8_0", - "70b-v1-preview-llama-fp16" - ], - "qwen2.5vl": [ - "latest", - "3b", - "7b", - "32b", - "72b", - "3b-q4_K_M", - "3b-q8_0", - "3b-fp16", - "7b-q4_K_M", - "7b-q8_0", - "7b-fp16", - "32b-q4_K_M", - "32b-q8_0", - "32b-fp16", - "72b-q4_K_M", - "72b-q8_0", - "72b-fp16" - ], - "mistral-small3.2": [ - "latest", - "24b", - "24b-instruct-2506-q4_K_M", - "24b-instruct-2506-q8_0", - "24b-instruct-2506-fp16" - ], - "dolphin-phi": [ - "latest", - "2.7b", - "2.7b-v2.6", - "2.7b-v2.6-q2_K", - "2.7b-v2.6-q3_K_S", - "2.7b-v2.6-q3_K_M", - "2.7b-v2.6-q3_K_L", - "2.7b-v2.6-q4_0", - "2.7b-v2.6-q4_K_S", - "2.7b-v2.6-q4_K_M", - "2.7b-v2.6-q5_0", - "2.7b-v2.6-q5_K_S", - "2.7b-v2.6-q5_K_M", - "2.7b-v2.6-q6_K", - "2.7b-v2.6-q8_0" - ], - "gemma3n": [ - "latest", - "e2b", - "e4b", - "e2b-it-q4_K_M", - "e2b-it-q8_0", - "e2b-it-fp16", - "e4b-it-q4_K_M", - "e4b-it-q8_0", - "e4b-it-fp16" - ], - "deepscaler": [ - "latest", - "1.5b", - "1.5b-preview-q4_K_M", - "1.5b-preview-q8_0", - "1.5b-preview-fp16" - ], - "llama4": [ - "latest", - "maverick", - "scout", - "16x17b", - "128x17b", - "17b-maverick-128e-instruct-q4_K_M", - "17b-maverick-128e-instruct-q8_0", - "17b-maverick-128e-instruct-fp16", - "17b-scout-16e-instruct-q4_K_M", - "17b-scout-16e-instruct-q8_0", - "17b-scout-16e-instruct-fp16" - ], - "phi4-reasoning": [ - "latest", - "plus", - "14b", - "14b-plus-q4_K_M", - "14b-plus-q8_0", - "14b-plus-fp16", - "14b-q4_K_M", - "14b-q8_0", - "14b-fp16" - ], - "magistral": [ - "latest", - "24b", - "24b-small-2506-q4_K_M", - "24b-small-2506-q8_0", - "24b-small-2506-fp16" - ], - "phi": [ - "latest", - "chat", - "2.7b", - "2.7b-chat-v2-q2_K", - "2.7b-chat-v2-q3_K_S", - "2.7b-chat-v2-q3_K_M", - "2.7b-chat-v2-q3_K_L", - "2.7b-chat-v2-q4_0", - "2.7b-chat-v2-q4_1", - "2.7b-chat-v2-q4_K_S", - "2.7b-chat-v2-q4_K_M", - "2.7b-chat-v2-q5_0", - "2.7b-chat-v2-q5_1", - "2.7b-chat-v2-q5_K_S", - "2.7b-chat-v2-q5_K_M", - "2.7b-chat-v2-q6_K", - "2.7b-chat-v2-q8_0", - "2.7b-chat-v2-fp16" - ], - "dolphin-mixtral": [ - "latest", - "v2.5", - "v2.6", - "v2.7", - "8x7b", - "8x22b", - "8x7b-v2.5", - "8x7b-v2.5-q2_K", - "8x7b-v2.5-q3_K_S", - "8x7b-v2.5-q3_K_M", - "8x7b-v2.5-q3_K_L", - "8x7b-v2.5-q4_0", - "8x7b-v2.5-q4_1", - "8x7b-v2.5-q4_K_S", - "8x7b-v2.5-q4_K_M", - "8x7b-v2.5-q5_0", - "8x7b-v2.5-q5_1", - "8x7b-v2.5-q5_K_S", - "8x7b-v2.5-q5_K_M", - "8x7b-v2.5-q6_K", - "8x7b-v2.5-q8_0", - "8x7b-v2.5-fp16", - "8x7b-v2.6", - "8x7b-v2.6-q2_K", - "8x7b-v2.6-q3_K_S", - "8x7b-v2.6-q3_K_M", - "8x7b-v2.6-q3_K_L", - "8x7b-v2.6-q4_0", - "8x7b-v2.6-q4_1", - "8x7b-v2.6-q4_K_S", - "8x7b-v2.6-q4_K_M", - "8x7b-v2.6-q5_0", - "8x7b-v2.6-q5_1", - "8x7b-v2.6-q5_K_S", - "8x7b-v2.6-q5_K_M", - "8x7b-v2.6-q6_K", - "8x7b-v2.6-q8_0", - "8x7b-v2.6-fp16", - "8x7b-v2.7", - "8x7b-v2.7-q2_K", - "8x7b-v2.7-q3_K_S", - "8x7b-v2.7-q3_K_M", - "8x7b-v2.7-q3_K_L", - "8x7b-v2.7-q4_0", - "8x7b-v2.7-q4_1", - "8x7b-v2.7-q4_K_S", - "8x7b-v2.7-q4_K_M", - "8x7b-v2.7-q5_0", - "8x7b-v2.7-q5_1", - "8x7b-v2.7-q5_K_S", - "8x7b-v2.7-q5_K_M", - "8x7b-v2.7-q6_K", - "8x7b-v2.7-q8_0", - "8x7b-v2.7-fp16", - "8x22b-v2.9", - "8x22b-v2.9-q2_K", - "8x22b-v2.9-q3_K_S", - "8x22b-v2.9-q3_K_M", - "8x22b-v2.9-q3_K_L", - "8x22b-v2.9-q4_0", - "8x22b-v2.9-q4_1", - "8x22b-v2.9-q4_K_S", - "8x22b-v2.9-q4_K_M", - "8x22b-v2.9-q5_0", - "8x22b-v2.9-q5_1", - "8x22b-v2.9-q5_K_S", - "8x22b-v2.9-q5_K_M", - "8x22b-v2.9-q6_K", - "8x22b-v2.9-q8_0", - "8x22b-v2.9-fp16" - ], - "granite3.3": [ - "latest", - "2b", - "8b" - ], - "dolphin-llama3": [ - "latest", - "v2.9", - "8b", - "70b", - "8b-256k", - "8b-256k-v2.9", - "8b-256k-v2.9-q2_K", - "8b-256k-v2.9-q3_K_S", - "8b-256k-v2.9-q3_K_M", - "8b-256k-v2.9-q3_K_L", - "8b-256k-v2.9-q4_0", - "8b-256k-v2.9-q4_1", - "8b-256k-v2.9-q4_K_S", - "8b-256k-v2.9-q4_K_M", - "8b-256k-v2.9-q5_0", - "8b-256k-v2.9-q5_1", - "8b-256k-v2.9-q5_K_S", - "8b-256k-v2.9-q5_K_M", - "8b-256k-v2.9-q6_K", - "8b-256k-v2.9-q8_0", - "8b-256k-v2.9-fp16", - "8b-v2.9", - "8b-v2.9-q2_K", - "8b-v2.9-q3_K_S", - "8b-v2.9-q3_K_M", - "8b-v2.9-q3_K_L", - "8b-v2.9-q4_0", - "8b-v2.9-q4_1", - "8b-v2.9-q4_K_S", - "8b-v2.9-q4_K_M", - "8b-v2.9-q5_0", - "8b-v2.9-q5_1", - "8b-v2.9-q5_K_S", - "8b-v2.9-q5_K_M", - "8b-v2.9-q6_K", - "8b-v2.9-q8_0", - "8b-v2.9-fp16", - "70b-v2.9", - "70b-v2.9-q2_K", - "70b-v2.9-q3_K_S", - "70b-v2.9-q3_K_M", - "70b-v2.9-q3_K_L", - "70b-v2.9-q4_0", - "70b-v2.9-q4_1", - "70b-v2.9-q4_K_S", - "70b-v2.9-q4_K_M", - "70b-v2.9-q5_0", - "70b-v2.9-q5_1", - "70b-v2.9-q5_K_S", - "70b-v2.9-q5_K_M", - "70b-v2.9-q6_K", - "70b-v2.9-q8_0", - "70b-v2.9-fp16" - ], - "phi4-mini": [ - "latest", - "3.8b", - "3.8b-q4_K_M", - "3.8b-q8_0", - "3.8b-fp16" - ], - "smollm": [ - "latest", - "135m", - "360m", - "1.7b", - "135m-base-v0.2-q2_K", - "135m-base-v0.2-q3_K_S", - "135m-base-v0.2-q3_K_M", - "135m-base-v0.2-q3_K_L", - "135m-base-v0.2-q4_0", - "135m-base-v0.2-q4_1", - "135m-base-v0.2-q4_K_S", - "135m-base-v0.2-q4_K_M", - "135m-base-v0.2-q5_0", - "135m-base-v0.2-q5_1", - "135m-base-v0.2-q5_K_S", - "135m-base-v0.2-q5_K_M", - "135m-base-v0.2-q6_K", - "135m-base-v0.2-q8_0", - "135m-base-v0.2-fp16", - "135m-instruct-v0.2-q2_K", - "135m-instruct-v0.2-q3_K_S", - "135m-instruct-v0.2-q3_K_M", - "135m-instruct-v0.2-q3_K_L", - "135m-instruct-v0.2-q4_0", - "135m-instruct-v0.2-q4_1", - "135m-instruct-v0.2-q4_K_S", - "135m-instruct-v0.2-q4_K_M", - "135m-instruct-v0.2-q5_0", - "135m-instruct-v0.2-q5_1", - "135m-instruct-v0.2-q5_K_S", - "135m-instruct-v0.2-q5_K_M", - "135m-instruct-v0.2-q6_K", - "135m-instruct-v0.2-q8_0", - "135m-instruct-v0.2-fp16", - "360m-base-v0.2-q2_K", - "360m-base-v0.2-q3_K_S", - "360m-base-v0.2-q3_K_M", - "360m-base-v0.2-q3_K_L", - "360m-base-v0.2-q4_0", - "360m-base-v0.2-q4_1", - "360m-base-v0.2-q4_K_S", - "360m-base-v0.2-q4_K_M", - "360m-base-v0.2-q5_0", - "360m-base-v0.2-q5_1", - "360m-base-v0.2-q5_K_S", - "360m-base-v0.2-q5_K_M", - "360m-base-v0.2-q6_K", - "360m-base-v0.2-q8_0", - "360m-base-v0.2-fp16", - "360m-instruct-v0.2-q2_K", - "360m-instruct-v0.2-q3_K_S", - "360m-instruct-v0.2-q3_K_M", - "360m-instruct-v0.2-q3_K_L", - "360m-instruct-v0.2-q4_0", - "360m-instruct-v0.2-q4_1", - "360m-instruct-v0.2-q4_K_S", - "360m-instruct-v0.2-q4_K_M", - "360m-instruct-v0.2-q5_0", - "360m-instruct-v0.2-q5_1", - "360m-instruct-v0.2-q5_K_S", - "360m-instruct-v0.2-q5_K_M", - "360m-instruct-v0.2-q6_K", - "360m-instruct-v0.2-q8_0", - "360m-instruct-v0.2-fp16", - "1.7b-base-v0.2-q2_K", - "1.7b-base-v0.2-q3_K_S", - "1.7b-base-v0.2-q3_K_M", - "1.7b-base-v0.2-q3_K_L", - "1.7b-base-v0.2-q4_0", - "1.7b-base-v0.2-q4_1", - "1.7b-base-v0.2-q4_K_S", - "1.7b-base-v0.2-q4_K_M", - "1.7b-base-v0.2-q5_0", - "1.7b-base-v0.2-q5_1", - "1.7b-base-v0.2-q5_K_S", - "1.7b-base-v0.2-q5_K_M", - "1.7b-base-v0.2-q6_K", - "1.7b-base-v0.2-q8_0", - "1.7b-base-v0.2-fp16", - "1.7b-instruct-v0.2-q2_K", - "1.7b-instruct-v0.2-q3_K_S", - "1.7b-instruct-v0.2-q3_K_M", - "1.7b-instruct-v0.2-q3_K_L", - "1.7b-instruct-v0.2-q4_0", - "1.7b-instruct-v0.2-q4_1", - "1.7b-instruct-v0.2-q4_K_S", - "1.7b-instruct-v0.2-q4_K_M", - "1.7b-instruct-v0.2-q5_0", - "1.7b-instruct-v0.2-q5_1", - "1.7b-instruct-v0.2-q5_K_S", - "1.7b-instruct-v0.2-q5_K_M", - "1.7b-instruct-v0.2-q6_K", - "1.7b-instruct-v0.2-q8_0", - "1.7b-instruct-v0.2-fp16" - ], - "openthinker": [ - "latest", - "7b", - "32b", - "7b-v2-q4_K_M", - "7b-v2-q8_0", - "7b-v2-fp16", - "7b-q4_K_M", - "7b-q8_0", - "7b-fp16", - "32b-v2-q4_K_M", - "32b-v2-q8_0", - "32b-v2-fp16", - "32b-q4_K_M", - "32b-q8_0", - "32b-fp16" - ], - "codestral": [ - "latest", - "v0.1", - "22b", - "22b-v0.1-q2_K", - "22b-v0.1-q3_K_S", - "22b-v0.1-q3_K_M", - "22b-v0.1-q3_K_L", - "22b-v0.1-q4_0", - "22b-v0.1-q4_1", - "22b-v0.1-q4_K_S", - "22b-v0.1-q4_K_M", - "22b-v0.1-q5_0", - "22b-v0.1-q5_1", - "22b-v0.1-q5_K_S", - "22b-v0.1-q5_K_M", - "22b-v0.1-q6_K", - "22b-v0.1-q8_0" - ], - "granite3.2-vision": [ - "latest", - "2b", - "2b-q4_K_M", - "2b-q8_0", - "2b-fp16" - ], - "devstral": [ - "latest", - "24b", - "24b-small-2505-q4_K_M", - "24b-small-2505-q8_0", - "24b-small-2505-fp16" - ], - "dolphin-mistral": [ - "latest", - "v2", - "v2.1", - "v2.2", - "v2.2.1", - "v2.6", - "v2.8", - "7b", - "7b-v2", - "7b-v2-q2_K", - "7b-v2-q3_K_S", - "7b-v2-q3_K_M", - "7b-v2-q3_K_L", - "7b-v2-q4_0", - "7b-v2-q4_1", - "7b-v2-q4_K_S", - "7b-v2-q4_K_M", - "7b-v2-q5_0", - "7b-v2-q5_1", - "7b-v2-q5_K_S", - "7b-v2-q5_K_M", - "7b-v2-q6_K", - "7b-v2-q8_0", - "7b-v2-fp16", - "7b-v2.1", - "7b-v2.1-q2_K", - "7b-v2.1-q3_K_S", - "7b-v2.1-q3_K_M", - "7b-v2.1-q3_K_L", - "7b-v2.1-q4_0", - "7b-v2.1-q4_1", - "7b-v2.1-q4_K_S", - "7b-v2.1-q4_K_M", - "7b-v2.1-q5_0", - "7b-v2.1-q5_1", - "7b-v2.1-q5_K_S", - "7b-v2.1-q5_K_M", - "7b-v2.1-q6_K", - "7b-v2.1-q8_0", - "7b-v2.1-fp16", - "7b-v2.2", - "7b-v2.2-q2_K", - "7b-v2.2-q3_K_S", - "7b-v2.2-q3_K_M", - "7b-v2.2-q3_K_L", - "7b-v2.2-q4_0", - "7b-v2.2-q4_1", - "7b-v2.2-q4_K_S", - "7b-v2.2-q4_K_M", - "7b-v2.2-q5_0", - "7b-v2.2-q5_1", - "7b-v2.2-q5_K_S", - "7b-v2.2-q5_K_M", - "7b-v2.2-q6_K", - "7b-v2.2-q8_0", - "7b-v2.2-fp16", - "7b-v2.2.1", - "7b-v2.2.1-q2_K", - "7b-v2.2.1-q3_K_S", - "7b-v2.2.1-q3_K_M", - "7b-v2.2.1-q3_K_L", - "7b-v2.2.1-q4_0", - "7b-v2.2.1-q4_1", - "7b-v2.2.1-q4_K_S", - "7b-v2.2.1-q4_K_M", - "7b-v2.2.1-q5_0", - "7b-v2.2.1-q5_1", - "7b-v2.2.1-q5_K_S", - "7b-v2.2.1-q5_K_M", - "7b-v2.2.1-q6_K", - "7b-v2.2.1-q8_0", - "7b-v2.2.1-fp16", - "7b-v2.6", - "7b-v2.6-dpo-laser", - "7b-v2.6-dpo-laser-q2_K", - "7b-v2.6-q2_K", - "7b-v2.6-dpo-laser-q3_K_S", - "7b-v2.6-q3_K_S", - "7b-v2.6-dpo-laser-q3_K_M", - "7b-v2.6-q3_K_M", - "7b-v2.6-dpo-laser-q3_K_L", - "7b-v2.6-q3_K_L", - "7b-v2.6-dpo-laser-q4_0", - "7b-v2.6-q4_0", - "7b-v2.6-dpo-laser-q4_1", - "7b-v2.6-q4_1", - "7b-v2.6-dpo-laser-q4_K_S", - "7b-v2.6-q4_K_S", - "7b-v2.6-dpo-laser-q4_K_M", - "7b-v2.6-q4_K_M", - "7b-v2.6-dpo-laser-q5_0", - "7b-v2.6-q5_0", - "7b-v2.6-dpo-laser-q5_1", - "7b-v2.6-q5_1", - "7b-v2.6-dpo-laser-q5_K_S", - "7b-v2.6-q5_K_S", - "7b-v2.6-dpo-laser-q5_K_M", - "7b-v2.6-q5_K_M", - "7b-v2.6-dpo-laser-q6_K", - "7b-v2.6-q6_K", - "7b-v2.6-dpo-laser-q8_0", - "7b-v2.6-q8_0", - "7b-v2.6-dpo-laser-fp16", - "7b-v2.6-fp16", - "7b-v2.8", - "7b-v2.8-q2_K", - "7b-v2.8-q3_K_S", - "7b-v2.8-q3_K_M", - "7b-v2.8-q3_K_L", - "7b-v2.8-q4_0", - "7b-v2.8-q4_1", - "7b-v2.8-q4_K_S", - "7b-v2.8-q4_K_M", - "7b-v2.8-q5_0", - "7b-v2.8-q5_1", - "7b-v2.8-q5_K_S", - "7b-v2.8-q5_K_M", - "7b-v2.8-q6_K", - "7b-v2.8-q8_0", - "7b-v2.8-fp16" - ], - "wizardlm2": [ - "latest", - "7b", - "8x22b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "8x22b-q2_K", - "8x22b-q4_0", - "8x22b-q8_0", - "8x22b-fp16" - ], - "command-r": [ - "latest", - "v0.1", - "35b", - "35b-08-2024-q2_K", - "35b-08-2024-q3_K_S", - "35b-08-2024-q3_K_M", - "35b-08-2024-q3_K_L", - "35b-08-2024-q4_0", - "35b-08-2024-q4_1", - "35b-08-2024-q4_K_S", - "35b-08-2024-q4_K_M", - "35b-08-2024-q5_0", - "35b-08-2024-q5_1", - "35b-08-2024-q5_K_S", - "35b-08-2024-q5_K_M", - "35b-08-2024-q6_K", - "35b-08-2024-q8_0", - "35b-08-2024-fp16", - "35b-v0.1-q2_K", - "35b-v0.1-q3_K_S", - "35b-v0.1-q3_K_M", - "35b-v0.1-q3_K_L", - "35b-v0.1-q4_0", - "35b-v0.1-q4_1", - "35b-v0.1-q4_K_S", - "35b-v0.1-q4_K_M", - "35b-v0.1-q5_1", - "35b-v0.1-q5_K_S", - "35b-v0.1-q5_K_M", - "35b-v0.1-q6_K", - "35b-v0.1-q8_0", - "35b-v0.1-fp16" - ], - "deepcoder": [ - "latest", - "1.5b", - "14b", - "1.5b-preview-q4_K_M", - "1.5b-preview-q8_0", - "1.5b-preview-fp16", - "14b-preview-q4_K_M", - "14b-preview-q8_0", - "14b-preview-fp16" - ], - "granite-code": [ - "latest", - "3b", - "8b", - "20b", - "34b", - "3b-base", - "3b-base-q2_K", - "3b-base-q3_K_S", - "3b-base-q3_K_M", - "3b-base-q3_K_L", - "3b-base-q4_0", - "3b-base-q4_1", - "3b-base-q4_K_S", - "3b-base-q4_K_M", - "3b-base-q5_0", - "3b-base-q5_1", - "3b-base-q5_K_S", - "3b-base-q5_K_M", - "3b-base-q6_K", - "3b-base-q8_0", - "3b-base-fp16", - "3b-instruct", - "3b-instruct-128k-q2_K", - "3b-instruct-q2_K", - "3b-instruct-128k-q3_K_S", - "3b-instruct-q3_K_S", - "3b-instruct-128k-q3_K_M", - "3b-instruct-q3_K_M", - "3b-instruct-128k-q3_K_L", - "3b-instruct-q3_K_L", - "3b-instruct-128k-q4_0", - "3b-instruct-q4_0", - "3b-instruct-128k-q4_1", - "3b-instruct-q4_1", - "3b-instruct-128k-q4_K_S", - "3b-instruct-q4_K_S", - "3b-instruct-128k-q4_K_M", - "3b-instruct-q4_K_M", - "3b-instruct-128k-q5_0", - "3b-instruct-q5_0", - "3b-instruct-128k-q5_1", - "3b-instruct-q5_1", - "3b-instruct-128k-q5_K_S", - "3b-instruct-q5_K_S", - "3b-instruct-128k-q5_K_M", - "3b-instruct-q5_K_M", - "3b-instruct-128k-q6_K", - "3b-instruct-q6_K", - "3b-instruct-128k-q8_0", - "3b-instruct-q8_0", - "3b-instruct-128k-fp16", - "3b-instruct-fp16", - "8b-base", - "8b-base-q2_K", - "8b-base-q3_K_S", - "8b-base-q3_K_M", - "8b-base-q3_K_L", - "8b-base-q4_0", - "8b-base-q4_1", - "8b-base-q4_K_S", - "8b-base-q4_K_M", - "8b-base-q5_0", - "8b-base-q5_1", - "8b-base-q5_K_S", - "8b-base-q5_K_M", - "8b-base-q6_K", - "8b-base-q8_0", - "8b-base-fp16", - "8b-instruct", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-128k-q4_0", - "8b-instruct-q4_0", - "8b-instruct-128k-q4_1", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16", - "20b-base", - "20b-base-q2_K", - "20b-base-q3_K_S", - "20b-base-q3_K_M", - "20b-base-q3_K_L", - "20b-base-q4_0", - "20b-base-q4_1", - "20b-base-q4_K_S", - "20b-base-q4_K_M", - "20b-base-q5_0", - "20b-base-q5_1", - "20b-base-q5_K_S", - "20b-base-q5_K_M", - "20b-base-q6_K", - "20b-base-q8_0", - "20b-base-fp16", - "20b-instruct", - "20b-instruct-8k-q2_K", - "20b-instruct-q2_K", - "20b-instruct-8k-q3_K_S", - "20b-instruct-q3_K_S", - "20b-instruct-8k-q3_K_M", - "20b-instruct-q3_K_M", - "20b-instruct-8k-q3_K_L", - "20b-instruct-q3_K_L", - "20b-instruct-8k-q4_0", - "20b-instruct-q4_0", - "20b-instruct-8k-q4_1", - "20b-instruct-q4_1", - "20b-instruct-8k-q4_K_S", - "20b-instruct-q4_K_S", - "20b-instruct-8k-q4_K_M", - "20b-instruct-q4_K_M", - "20b-instruct-8k-q5_0", - "20b-instruct-q5_0", - "20b-instruct-8k-q5_1", - "20b-instruct-q5_1", - "20b-instruct-8k-q5_K_S", - "20b-instruct-q5_K_S", - "20b-instruct-8k-q5_K_M", - "20b-instruct-q5_K_M", - "20b-instruct-8k-q6_K", - "20b-instruct-q6_K", - "20b-instruct-8k-q8_0", - "20b-instruct-q8_0", - "20b-instruct-8k-fp16", - "34b-base", - "34b-base-q2_K", - "34b-base-q3_K_S", - "34b-base-q3_K_M", - "34b-base-q3_K_L", - "34b-base-q4_0", - "34b-base-q4_1", - "34b-base-q4_K_S", - "34b-base-q4_K_M", - "34b-base-q5_0", - "34b-base-q5_1", - "34b-base-q5_K_S", - "34b-base-q5_K_M", - "34b-base-q6_K", - "34b-base-q8_0", - "34b-instruct", - "34b-instruct-q2_K", - "34b-instruct-q3_K_S", - "34b-instruct-q3_K_M", - "34b-instruct-q3_K_L", - "34b-instruct-q4_0", - "34b-instruct-q4_1", - "34b-instruct-q4_K_S", - "34b-instruct-q4_K_M", - "34b-instruct-q5_0", - "34b-instruct-q5_1", - "34b-instruct-q5_K_S", - "34b-instruct-q5_K_M", - "34b-instruct-q6_K", - "34b-instruct-q8_0" - ], - "moondream": [ - "latest", - "v2", - "1.8b", - "1.8b-v2-q2_K", - "1.8b-v2-q3_K_S", - "1.8b-v2-q3_K_M", - "1.8b-v2-q3_K_L", - "1.8b-v2-q4_0", - "1.8b-v2-q4_1", - "1.8b-v2-q4_K_S", - "1.8b-v2-q4_K_M", - "1.8b-v2-q5_0", - "1.8b-v2-q5_1", - "1.8b-v2-q5_K_S", - "1.8b-v2-q5_K_M", - "1.8b-v2-q6_K", - "1.8b-v2-q8_0", - "1.8b-v2-fp16" - ], - "mistral-small3.1": [ - "latest", - "24b", - "24b-instruct-2503-q4_K_M", - "24b-instruct-2503-q8_0", - "24b-instruct-2503-fp16" - ], - "granite4": [ - "latest", - "micro", - "350m", - "1b", - "3b", - "350m-h", - "350m-h-q8_0", - "350m-bf16", - "1b-h", - "1b-h-q8_0", - "1b-bf16", - "3b-h", - "7b-a1b-h", - "32b-a9b-h", - "micro-h", - "small-h", - "tiny-h" - ], - "hermes3": [ - "latest", - "3b", - "8b", - "70b", - "405b", - "3b-llama3.2-q2_K", - "3b-llama3.2-q3_K_S", - "3b-llama3.2-q3_K_M", - "3b-llama3.2-q3_K_L", - "3b-llama3.2-q4_0", - "3b-llama3.2-q4_1", - "3b-llama3.2-q4_K_S", - "3b-llama3.2-q4_K_M", - "3b-llama3.2-q5_0", - "3b-llama3.2-q5_1", - "3b-llama3.2-q5_K_S", - "3b-llama3.2-q5_K_M", - "3b-llama3.2-q6_K", - "3b-llama3.2-q8_0", - "3b-llama3.2-fp16", - "8b-llama3.1-q2_K", - "8b-llama3.1-q3_K_S", - "8b-llama3.1-q3_K_M", - "8b-llama3.1-q3_K_L", - "8b-llama3.1-q4_0", - "8b-llama3.1-q4_1", - "8b-llama3.1-q4_K_S", - "8b-llama3.1-q4_K_M", - "8b-llama3.1-q5_0", - "8b-llama3.1-q5_1", - "8b-llama3.1-q5_K_S", - "8b-llama3.1-q5_K_M", - "8b-llama3.1-q6_K", - "8b-llama3.1-q8_0", - "8b-llama3.1-fp16", - "70b-llama3.1-q2_K", - "70b-llama3.1-q3_K_S", - "70b-llama3.1-q3_K_M", - "70b-llama3.1-q3_K_L", - "70b-llama3.1-q4_0", - "70b-llama3.1-q4_1", - "70b-llama3.1-q4_K_S", - "70b-llama3.1-q4_K_M", - "70b-llama3.1-q5_0", - "70b-llama3.1-q5_1", - "70b-llama3.1-q5_K_S", - "70b-llama3.1-q5_K_M", - "70b-llama3.1-q6_K", - "70b-llama3.1-q8_0", - "70b-llama3.1-fp16", - "405b-llama3.1-q2_K", - "405b-llama3.1-q3_K_S", - "405b-llama3.1-q3_K_M", - "405b-llama3.1-q3_K_L", - "405b-llama3.1-q4_0", - "405b-llama3.1-q4_1", - "405b-llama3.1-q4_K_S", - "405b-llama3.1-q4_K_M", - "405b-llama3.1-q5_0", - "405b-llama3.1-q5_1", - "405b-llama3.1-q5_K_S", - "405b-llama3.1-q5_K_M", - "405b-llama3.1-q6_K", - "405b-llama3.1-q8_0", - "405b-llama3.1-fp16" - ], - "phi3.5": [ - "latest", - "3.8b", - "3.8b-mini-instruct-q2_K", - "3.8b-mini-instruct-q3_K_S", - "3.8b-mini-instruct-q3_K_M", - "3.8b-mini-instruct-q3_K_L", - "3.8b-mini-instruct-q4_0", - "3.8b-mini-instruct-q4_1", - "3.8b-mini-instruct-q4_K_S", - "3.8b-mini-instruct-q4_K_M", - "3.8b-mini-instruct-q5_0", - "3.8b-mini-instruct-q5_1", - "3.8b-mini-instruct-q5_K_S", - "3.8b-mini-instruct-q5_K_M", - "3.8b-mini-instruct-q6_K", - "3.8b-mini-instruct-q8_0", - "3.8b-mini-instruct-fp16" - ], - "yi": [ - "latest", - "v1.5", - "6b", - "9b", - "34b", - "6b-200k", - "6b-200k-q2_K", - "6b-200k-q3_K_S", - "6b-200k-q3_K_M", - "6b-200k-q3_K_L", - "6b-200k-q4_0", - "6b-200k-q4_1", - "6b-200k-q4_K_S", - "6b-200k-q4_K_M", - "6b-200k-q5_0", - "6b-200k-q5_1", - "6b-200k-q5_K_S", - "6b-200k-q5_K_M", - "6b-200k-q6_K", - "6b-200k-q8_0", - "6b-200k-fp16", - "6b-chat", - "6b-chat-q2_K", - "6b-chat-v1.5-q2_K", - "6b-chat-q3_K_S", - "6b-chat-v1.5-q3_K_S", - "6b-chat-q3_K_M", - "6b-chat-v1.5-q3_K_M", - "6b-chat-q3_K_L", - "6b-chat-v1.5-q3_K_L", - "6b-chat-q4_0", - "6b-chat-v1.5-q4_0", - "6b-chat-q4_1", - "6b-chat-v1.5-q4_1", - "6b-chat-q4_K_S", - "6b-chat-v1.5-q4_K_S", - "6b-chat-q4_K_M", - "6b-chat-v1.5-q4_K_M", - "6b-chat-q5_0", - "6b-chat-v1.5-q5_0", - "6b-chat-q5_1", - "6b-chat-v1.5-q5_1", - "6b-chat-q5_K_S", - "6b-chat-v1.5-q5_K_S", - "6b-chat-q5_K_M", - "6b-chat-v1.5-q5_K_M", - "6b-chat-q6_K", - "6b-chat-v1.5-q6_K", - "6b-chat-q8_0", - "6b-chat-v1.5-q8_0", - "6b-chat-fp16", - "6b-chat-v1.5-fp16", - "6b-v1.5", - "6b-v1.5-q2_K", - "6b-v1.5-q3_K_S", - "6b-v1.5-q3_K_M", - "6b-v1.5-q3_K_L", - "6b-v1.5-q4_0", - "6b-v1.5-q4_1", - "6b-v1.5-q4_K_S", - "6b-v1.5-q4_K_M", - "6b-v1.5-q5_0", - "6b-v1.5-q5_1", - "6b-v1.5-q5_K_S", - "6b-v1.5-q5_K_M", - "6b-v1.5-q6_K", - "6b-v1.5-q8_0", - "6b-v1.5-fp16", - "6b-q2_K", - "6b-q3_K_S", - "6b-q3_K_M", - "6b-q3_K_L", - "6b-q4_0", - "6b-q4_1", - "6b-q4_K_S", - "6b-q4_K_M", - "6b-q5_0", - "6b-q5_1", - "6b-q5_K_S", - "6b-q5_K_M", - "6b-q6_K", - "6b-q8_0", - "6b-fp16", - "9b-chat", - "9b-chat-v1.5-q2_K", - "9b-chat-v1.5-q3_K_S", - "9b-chat-v1.5-q3_K_M", - "9b-chat-v1.5-q3_K_L", - "9b-chat-v1.5-q4_0", - "9b-chat-v1.5-q4_1", - "9b-chat-v1.5-q4_K_S", - "9b-chat-v1.5-q4_K_M", - "9b-chat-v1.5-q5_0", - "9b-chat-v1.5-q5_1", - "9b-chat-v1.5-q5_K_S", - "9b-chat-v1.5-q5_K_M", - "9b-chat-v1.5-q6_K", - "9b-chat-v1.5-q8_0", - "9b-chat-v1.5-fp16", - "9b-v1.5", - "9b-v1.5-q2_K", - "9b-v1.5-q3_K_S", - "9b-v1.5-q3_K_M", - "9b-v1.5-q3_K_L", - "9b-v1.5-q4_0", - "9b-v1.5-q4_1", - "9b-v1.5-q4_K_S", - "9b-v1.5-q4_K_M", - "9b-v1.5-q5_0", - "9b-v1.5-q5_1", - "9b-v1.5-q5_K_S", - "9b-v1.5-q5_K_M", - "9b-v1.5-q6_K", - "9b-v1.5-q8_0", - "9b-v1.5-fp16", - "34b-chat", - "34b-chat-q2_K", - "34b-chat-v1.5-q2_K", - "34b-chat-q3_K_S", - "34b-chat-v1.5-q3_K_S", - "34b-chat-q3_K_M", - "34b-chat-v1.5-q3_K_M", - "34b-chat-q3_K_L", - "34b-chat-v1.5-q3_K_L", - "34b-chat-q4_0", - "34b-chat-v1.5-q4_0", - "34b-chat-q4_1", - "34b-chat-v1.5-q4_1", - "34b-chat-q4_K_S", - "34b-chat-v1.5-q4_K_S", - "34b-chat-q4_K_M", - "34b-chat-v1.5-q4_K_M", - "34b-chat-q5_0", - "34b-chat-v1.5-q5_0", - "34b-chat-q5_1", - "34b-chat-v1.5-q5_1", - "34b-chat-q5_K_S", - "34b-chat-v1.5-q5_K_S", - "34b-chat-q5_K_M", - "34b-chat-v1.5-q5_K_M", - "34b-chat-q6_K", - "34b-chat-v1.5-q6_K", - "34b-chat-q8_0", - "34b-chat-v1.5-q8_0", - "34b-chat-fp16", - "34b-chat-v1.5-fp16", - "34b-v1.5", - "34b-v1.5-q2_K", - "34b-v1.5-q3_K_S", - "34b-v1.5-q3_K_M", - "34b-v1.5-q3_K_L", - "34b-v1.5-q4_0", - "34b-v1.5-q4_1", - "34b-v1.5-q4_K_S", - "34b-v1.5-q4_K_M", - "34b-v1.5-q5_0", - "34b-v1.5-q5_1", - "34b-v1.5-q5_K_S", - "34b-v1.5-q5_K_M", - "34b-v1.5-q6_K", - "34b-v1.5-q8_0", - "34b-v1.5-fp16", - "34b-q2_K", - "34b-q3_K_S", - "34b-q3_K_M", - "34b-q3_K_L", - "34b-q4_0", - "34b-q4_1", - "34b-q4_K_S", - "34b-q4_K_M", - "34b-q5_0", - "34b-q5_1", - "34b-q5_K_S", - "34b-q6_K" - ], - "bakllava": [ - "latest", - "7b", - "7b-v1-q2_K", - "7b-v1-q3_K_S", - "7b-v1-q3_K_M", - "7b-v1-q3_K_L", - "7b-v1-q4_0", - "7b-v1-q4_1", - "7b-v1-q4_K_S", - "7b-v1-q4_K_M", - "7b-v1-q5_0", - "7b-v1-q5_1", - "7b-v1-q5_K_S", - "7b-v1-q5_K_M", - "7b-v1-q6_K", - "7b-v1-q8_0", - "7b-v1-fp16" - ], - "zephyr": [ - "latest", - "7b", - "141b", - "7b-alpha", - "7b-alpha-q2_K", - "7b-alpha-q3_K_S", - "7b-alpha-q3_K_M", - "7b-alpha-q3_K_L", - "7b-alpha-q4_0", - "7b-alpha-q4_1", - "7b-alpha-q4_K_S", - "7b-alpha-q4_K_M", - "7b-alpha-q5_0", - "7b-alpha-q5_1", - "7b-alpha-q5_K_S", - "7b-alpha-q5_K_M", - "7b-alpha-q6_K", - "7b-alpha-q8_0", - "7b-alpha-fp16", - "7b-beta", - "7b-beta-q2_K", - "7b-beta-q3_K_S", - "7b-beta-q3_K_M", - "7b-beta-q3_K_L", - "7b-beta-q4_0", - "7b-beta-q4_1", - "7b-beta-q4_K_S", - "7b-beta-q4_K_M", - "7b-beta-q5_0", - "7b-beta-q5_1", - "7b-beta-q5_K_S", - "7b-beta-q5_K_M", - "7b-beta-q6_K", - "7b-beta-q8_0", - "7b-beta-fp16", - "141b-v0.1", - "141b-v0.1-q2_K", - "141b-v0.1-q4_0", - "141b-v0.1-q8_0", - "141b-v0.1-fp16" - ], - "mistral-large": [ - "latest", - "123b", - "123b-instruct-2407-q2_K", - "123b-instruct-2407-q3_K_S", - "123b-instruct-2407-q3_K_M", - "123b-instruct-2407-q3_K_L", - "123b-instruct-2407-q4_0", - "123b-instruct-2407-q4_1", - "123b-instruct-2407-q4_K_S", - "123b-instruct-2407-q4_K_M", - "123b-instruct-2407-q5_0", - "123b-instruct-2407-q5_1", - "123b-instruct-2407-q5_K_S", - "123b-instruct-2407-q5_K_M", - "123b-instruct-2407-q6_K", - "123b-instruct-2407-q8_0", - "123b-instruct-2407-fp16", - "123b-instruct-2411-q2_K", - "123b-instruct-2411-q3_K_S", - "123b-instruct-2411-q3_K_M", - "123b-instruct-2411-q3_K_L", - "123b-instruct-2411-q4_0", - "123b-instruct-2411-q4_1", - "123b-instruct-2411-q4_K_S", - "123b-instruct-2411-q4_K_M", - "123b-instruct-2411-q5_0", - "123b-instruct-2411-q5_1", - "123b-instruct-2411-q5_K_S", - "123b-instruct-2411-q5_K_M", - "123b-instruct-2411-q6_K", - "123b-instruct-2411-q8_0", - "123b-instruct-2411-fp16" - ], - "wizard-vicuna-uncensored": [ - "latest", - "7b", - "13b", - "30b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "30b-q2_K", - "30b-q3_K_S", - "30b-q3_K_M", - "30b-q3_K_L", - "30b-q4_0", - "30b-q4_1", - "30b-q4_K_S", - "30b-q4_K_M", - "30b-q5_0", - "30b-q5_1", - "30b-q5_K_S", - "30b-q5_K_M", - "30b-q6_K", - "30b-q8_0", - "30b-fp16" - ], - "exaone-deep": [ - "latest", - "2.4b", - "7.8b", - "32b", - "2.4b-q4_K_M", - "2.4b-q8_0", - "2.4b-fp16", - "7.8b-q4_K_M", - "7.8b-q8_0", - "7.8b-fp16", - "32b-q4_K_M", - "32b-q8_0", - "32b-fp16" - ], - "embeddinggemma": [ - "latest", - "300m", - "300m-qat-q4_0", - "300m-qat-q8_0", - "300m-bf16" - ], - "starcoder": [ - "latest", - "1b", - "3b", - "7b", - "15b", - "1b-base", - "1b-base-q2_K", - "1b-base-q3_K_S", - "1b-base-q3_K_M", - "1b-base-q3_K_L", - "1b-base-q4_0", - "1b-base-q4_1", - "1b-base-q4_K_S", - "1b-base-q4_K_M", - "1b-base-q5_0", - "1b-base-q5_1", - "1b-base-q5_K_S", - "1b-base-q5_K_M", - "1b-base-q6_K", - "1b-base-q8_0", - "1b-base-fp16", - "3b-base", - "3b-base-q2_K", - "3b-base-q3_K_S", - "3b-base-q3_K_M", - "3b-base-q3_K_L", - "3b-base-q4_0", - "3b-base-q4_1", - "3b-base-q4_K_S", - "3b-base-q4_K_M", - "3b-base-q5_0", - "3b-base-q5_1", - "3b-base-q5_K_S", - "3b-base-q5_K_M", - "3b-base-q6_K", - "3b-base-q8_0", - "3b-base-fp16", - "7b-base", - "7b-base-q2_K", - "7b-base-q3_K_S", - "7b-base-q3_K_M", - "7b-base-q3_K_L", - "7b-base-q4_0", - "7b-base-q4_1", - "7b-base-q4_K_S", - "7b-base-q4_K_M", - "7b-base-q5_0", - "7b-base-q5_1", - "7b-base-q5_K_S", - "7b-base-q5_K_M", - "7b-base-q6_K", - "7b-base-q8_0", - "7b-base-fp16", - "15b-base", - "15b-base-q2_K", - "15b-base-q3_K_S", - "15b-base-q3_K_M", - "15b-base-q3_K_L", - "15b-base-q4_0", - "15b-base-q4_1", - "15b-base-q4_K_S", - "15b-base-q4_K_M", - "15b-base-q5_0", - "15b-base-q5_1", - "15b-base-q5_K_S", - "15b-base-q5_K_M", - "15b-base-q6_K", - "15b-base-q8_0", - "15b-base-fp16", - "15b-plus", - "15b-plus-q2_K", - "15b-plus-q3_K_S", - "15b-plus-q3_K_M", - "15b-plus-q3_K_L", - "15b-plus-q4_0", - "15b-plus-q4_1", - "15b-plus-q4_K_S", - "15b-plus-q4_K_M", - "15b-plus-q5_0", - "15b-plus-q5_1", - "15b-plus-q5_K_S", - "15b-plus-q5_K_M", - "15b-plus-q6_K", - "15b-plus-q8_0", - "15b-plus-fp16", - "15b-q2_K", - "15b-q3_K_S", - "15b-q3_K_M", - "15b-q3_K_L", - "15b-q4_0", - "15b-q4_1", - "15b-q4_K_S", - "15b-q4_K_M", - "15b-q5_0", - "15b-q5_1", - "15b-q5_K_S", - "15b-q5_K_M", - "15b-q6_K", - "15b-q8_0", - "15b-fp16" - ], - "nous-hermes": [ - "latest", - "7b", - "13b", - "7b-llama2", - "7b-llama2-q2_K", - "7b-llama2-q3_K_S", - "7b-llama2-q3_K_M", - "7b-llama2-q3_K_L", - "7b-llama2-q4_0", - "7b-llama2-q4_1", - "7b-llama2-q4_K_S", - "7b-llama2-q4_K_M", - "7b-llama2-q5_0", - "7b-llama2-q5_1", - "7b-llama2-q5_K_S", - "7b-llama2-q5_K_M", - "7b-llama2-q6_K", - "7b-llama2-q8_0", - "7b-llama2-fp16", - "13b-llama2", - "13b-llama2-q2_K", - "13b-llama2-q3_K_S", - "13b-llama2-q3_K_M", - "13b-llama2-q3_K_L", - "13b-llama2-q4_0", - "13b-llama2-q4_1", - "13b-llama2-q4_K_S", - "13b-llama2-q4_K_M", - "13b-llama2-q5_0", - "13b-llama2-q5_1", - "13b-llama2-q5_K_S", - "13b-llama2-q5_K_M", - "13b-llama2-q6_K", - "13b-llama2-q8_0", - "13b-llama2-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "70b-llama2-q2_K", - "70b-llama2-q3_K_S", - "70b-llama2-q3_K_M", - "70b-llama2-q3_K_L", - "70b-llama2-q4_0", - "70b-llama2-q4_1", - "70b-llama2-q4_K_S", - "70b-llama2-q4_K_M", - "70b-llama2-q5_0", - "70b-llama2-q5_1", - "70b-llama2-q5_K_M", - "70b-llama2-q6_K", - "70b-llama2-fp16" - ], - "deepseek-llm": [ - "latest", - "7b", - "67b", - "7b-base", - "7b-base-q2_K", - "7b-base-q3_K_S", - "7b-base-q3_K_M", - "7b-base-q3_K_L", - "7b-base-q4_0", - "7b-base-q4_1", - "7b-base-q4_K_S", - "7b-base-q4_K_M", - "7b-base-q5_0", - "7b-base-q5_1", - "7b-base-q5_K_S", - "7b-base-q5_K_M", - "7b-base-q6_K", - "7b-base-q8_0", - "7b-base-fp16", - "7b-chat", - "7b-chat-q2_K", - "7b-chat-q3_K_S", - "7b-chat-q3_K_M", - "7b-chat-q3_K_L", - "7b-chat-q4_0", - "7b-chat-q4_1", - "7b-chat-q4_K_S", - "7b-chat-q4_K_M", - "7b-chat-q5_0", - "7b-chat-q5_1", - "7b-chat-q5_K_S", - "7b-chat-q5_K_M", - "7b-chat-q6_K", - "7b-chat-q8_0", - "7b-chat-fp16", - "67b-base", - "67b-base-q2_K", - "67b-base-q3_K_S", - "67b-base-q3_K_M", - "67b-base-q3_K_L", - "67b-base-q4_0", - "67b-base-q4_1", - "67b-base-q4_K_S", - "67b-base-q4_K_M", - "67b-base-q5_0", - "67b-base-q5_1", - "67b-base-q5_K_S", - "67b-base-q5_K_M", - "67b-base-q6_K", - "67b-base-q8_0", - "67b-base-fp16", - "67b-chat", - "67b-chat-q2_K", - "67b-chat-q3_K_S", - "67b-chat-q3_K_M", - "67b-chat-q3_K_L", - "67b-chat-q4_0", - "67b-chat-q4_1", - "67b-chat-q4_K_S", - "67b-chat-q4_K_M", - "67b-chat-q5_0", - "67b-chat-q5_1", - "67b-chat-q5_K_S", - "67b-chat-fp16" - ], - "falcon": [ - "latest", - "instruct", - "text", - "7b", - "40b", - "180b", - "7b-instruct", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "7b-text", - "7b-text-q4_0", - "7b-text-q4_1", - "7b-text-q5_0", - "7b-text-q5_1", - "7b-text-q8_0", - "7b-text-fp16", - "40b-instruct", - "40b-instruct-q4_0", - "40b-instruct-q4_1", - "40b-instruct-q5_0", - "40b-instruct-q5_1", - "40b-instruct-q8_0", - "40b-instruct-fp16", - "40b-text", - "40b-text-q4_0", - "40b-text-q4_1", - "40b-text-q5_0", - "40b-text-q5_1", - "40b-text-q8_0", - "40b-text-fp16", - "180b-chat", - "180b-chat-q4_0", - "180b-text", - "180b-text-q4_0" - ], - "opencoder": [ - "latest", - "1.5b", - "8b", - "1.5b-instruct-q4_K_M", - "1.5b-instruct-q8_0", - "1.5b-instruct-fp16", - "8b-instruct-q4_K_M", - "8b-instruct-q8_0", - "8b-instruct-fp16" - ], - "openchat": [ - "latest", - "7b", - "7b-v3.5", - "7b-v3.5-0106", - "7b-v3.5-0106-q2_K", - "7b-v3.5-q2_K", - "7b-v3.5-0106-q3_K_S", - "7b-v3.5-q3_K_S", - "7b-v3.5-0106-q3_K_M", - "7b-v3.5-q3_K_M", - "7b-v3.5-0106-q3_K_L", - "7b-v3.5-q3_K_L", - "7b-v3.5-0106-q4_0", - "7b-v3.5-q4_0", - "7b-v3.5-0106-q4_1", - "7b-v3.5-q4_1", - "7b-v3.5-0106-q4_K_S", - "7b-v3.5-q4_K_S", - "7b-v3.5-0106-q4_K_M", - "7b-v3.5-q4_K_M", - "7b-v3.5-0106-q5_0", - "7b-v3.5-q5_0", - "7b-v3.5-0106-q5_1", - "7b-v3.5-q5_1", - "7b-v3.5-0106-q5_K_S", - "7b-v3.5-0106-q5_K_M", - "7b-v3.5-0106-q6_K", - "7b-v3.5-0106-q8_0", - "7b-v3.5-0106-fp16", - "7b-v3.5-1210", - "7b-v3.5-1210-q2_K", - "7b-v3.5-1210-q3_K_S", - "7b-v3.5-1210-q3_K_M", - "7b-v3.5-1210-q3_K_L", - "7b-v3.5-1210-q4_0", - "7b-v3.5-1210-q4_1", - "7b-v3.5-1210-q4_K_S", - "7b-v3.5-1210-q4_K_M", - "7b-v3.5-1210-q5_0", - "7b-v3.5-1210-q5_1", - "7b-v3.5-1210-q5_K_S", - "7b-v3.5-q5_K_S", - "7b-v3.5-1210-q5_K_M", - "7b-v3.5-q5_K_M", - "7b-v3.5-1210-q6_K", - "7b-v3.5-q6_K", - "7b-v3.5-1210-q8_0", - "7b-v3.5-q8_0", - "7b-v3.5-1210-fp16", - "7b-v3.5-fp16" - ], - "vicuna": [ - "latest", - "7b", - "13b", - "33b", - "7b-16k", - "7b-v1.5-16k-q2_K", - "7b-v1.5-q2_K", - "7b-v1.5-16k-q3_K_S", - "7b-v1.5-q3_K_S", - "7b-v1.5-16k-q3_K_M", - "7b-v1.5-q3_K_M", - "7b-v1.5-16k-q3_K_L", - "7b-v1.5-q3_K_L", - "7b-v1.5-16k-q4_0", - "7b-v1.5-q4_0", - "7b-v1.5-16k-q4_1", - "7b-v1.5-q4_1", - "7b-v1.5-16k-q4_K_S", - "7b-v1.5-q4_K_S", - "7b-v1.5-16k-q4_K_M", - "7b-v1.5-q4_K_M", - "7b-v1.5-16k-q5_0", - "7b-v1.5-q5_0", - "7b-v1.5-16k-q5_1", - "7b-v1.5-q5_1", - "7b-v1.5-16k-q5_K_S", - "7b-v1.5-q5_K_S", - "7b-v1.5-16k-q5_K_M", - "7b-v1.5-q5_K_M", - "7b-v1.5-16k-q6_K", - "7b-v1.5-q6_K", - "7b-v1.5-16k-q8_0", - "7b-v1.5-q8_0", - "7b-v1.5-16k-fp16", - "7b-v1.5-fp16", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-16k", - "13b-v1.5-16k-q2_K", - "13b-v1.5-q2_K", - "13b-v1.5-16k-q3_K_S", - "13b-v1.5-q3_K_S", - "13b-v1.5-16k-q3_K_M", - "13b-v1.5-q3_K_M", - "13b-v1.5-16k-q3_K_L", - "13b-v1.5-q3_K_L", - "13b-v1.5-16k-q4_0", - "13b-v1.5-q4_0", - "13b-v1.5-16k-q4_1", - "13b-v1.5-q4_1", - "13b-v1.5-16k-q4_K_S", - "13b-v1.5-q4_K_S", - "13b-v1.5-16k-q4_K_M", - "13b-v1.5-q4_K_M", - "13b-v1.5-16k-q5_0", - "13b-v1.5-q5_0", - "13b-v1.5-16k-q5_1", - "13b-v1.5-q5_1", - "13b-v1.5-16k-q5_K_S", - "13b-v1.5-q5_K_S", - "13b-v1.5-16k-q5_K_M", - "13b-v1.5-q5_K_M", - "13b-v1.5-16k-q6_K", - "13b-v1.5-q6_K", - "13b-v1.5-16k-q8_0", - "13b-v1.5-q8_0", - "13b-v1.5-16k-fp16", - "13b-v1.5-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "33b-q2_K", - "33b-q3_K_S", - "33b-q3_K_M", - "33b-q3_K_L", - "33b-q4_0", - "33b-q4_1", - "33b-q4_K_S", - "33b-q4_K_M", - "33b-q5_0", - "33b-q5_1", - "33b-q5_K_S", - "33b-q5_K_M", - "33b-q6_K", - "33b-q8_0", - "33b-fp16" - ], - "deepseek-v2": [ - "latest", - "lite", - "16b", - "236b", - "16b-lite-chat-q2_K", - "16b-lite-chat-q3_K_S", - "16b-lite-chat-q3_K_M", - "16b-lite-chat-q3_K_L", - "16b-lite-chat-q4_0", - "16b-lite-chat-q4_1", - "16b-lite-chat-q4_K_S", - "16b-lite-chat-q4_K_M", - "16b-lite-chat-q5_0", - "16b-lite-chat-q5_1", - "16b-lite-chat-q5_K_S", - "16b-lite-chat-q5_K_M", - "16b-lite-chat-q6_K", - "16b-lite-chat-q8_0", - "16b-lite-chat-fp16", - "236b-chat-q2_K", - "236b-chat-q3_K_S", - "236b-chat-q3_K_M", - "236b-chat-q3_K_L", - "236b-chat-q4_0", - "236b-chat-q4_1", - "236b-chat-q4_K_S", - "236b-chat-q4_K_M", - "236b-chat-q5_0", - "236b-chat-q5_1", - "236b-chat-q5_K_S", - "236b-chat-q5_K_M", - "236b-chat-q6_K", - "236b-chat-q8_0", - "236b-chat-fp16" - ], - "openhermes": [ - "latest", - "v2", - "v2.5", - "7b-mistral-v2-q2_K", - "7b-mistral-v2-q3_K_S", - "7b-mistral-v2-q3_K_M", - "7b-mistral-v2-q3_K_L", - "7b-mistral-v2-q4_0", - "7b-mistral-v2-q4_1", - "7b-mistral-v2-q4_K_S", - "7b-mistral-v2-q4_K_M", - "7b-mistral-v2-q5_0", - "7b-mistral-v2-q5_1", - "7b-mistral-v2-q5_K_S", - "7b-mistral-v2-q5_K_M", - "7b-mistral-v2-q6_K", - "7b-mistral-v2-q8_0", - "7b-mistral-v2-fp16", - "7b-mistral-v2.5-q2_K", - "7b-mistral-v2.5-q3_K_S", - "7b-mistral-v2.5-q3_K_M", - "7b-mistral-v2.5-q3_K_L", - "7b-mistral-v2.5-q4_0", - "7b-mistral-v2.5-q4_1", - "7b-mistral-v2.5-q4_K_S", - "7b-mistral-v2.5-q4_K_M", - "7b-mistral-v2.5-q5_0", - "7b-mistral-v2.5-q5_1", - "7b-mistral-v2.5-q5_K_S", - "7b-mistral-v2.5-q5_K_M", - "7b-mistral-v2.5-q6_K", - "7b-mistral-v2.5-q8_0", - "7b-mistral-v2.5-fp16", - "7b-v2", - "7b-v2.5" - ], - "codeqwen": [ - "latest", - "chat", - "code", - "v1.5", - "7b", - "7b-chat", - "7b-chat-v1.5-q2_K", - "7b-chat-v1.5-q3_K_S", - "7b-chat-v1.5-q3_K_M", - "7b-chat-v1.5-q3_K_L", - "7b-chat-v1.5-q4_0", - "7b-chat-v1.5-q4_1", - "7b-chat-v1.5-q4_K_S", - "7b-chat-v1.5-q4_K_M", - "7b-chat-v1.5-q5_0", - "7b-chat-v1.5-q5_1", - "7b-chat-v1.5-q5_K_S", - "7b-chat-v1.5-q5_K_M", - "7b-chat-v1.5-q6_K", - "7b-chat-v1.5-q8_0", - "7b-chat-v1.5-fp16", - "7b-code", - "7b-code-v1.5-q4_0", - "7b-code-v1.5-q4_1", - "7b-code-v1.5-q5_0", - "7b-code-v1.5-q5_1", - "7b-code-v1.5-q8_0", - "7b-code-v1.5-fp16", - "v1.5-chat", - "v1.5-code" - ], - "paraphrase-multilingual": [ - "latest", - "278m", - "278m-mpnet-base-v2-fp16" - ], - "qwen2-math": [ - "latest", - "1.5b", - "7b", - "72b", - "1.5b-instruct", - "1.5b-instruct-q2_K", - "1.5b-instruct-q3_K_S", - "1.5b-instruct-q3_K_M", - "1.5b-instruct-q3_K_L", - "1.5b-instruct-q4_0", - "1.5b-instruct-q4_1", - "1.5b-instruct-q4_K_S", - "1.5b-instruct-q4_K_M", - "1.5b-instruct-q5_0", - "1.5b-instruct-q5_1", - "1.5b-instruct-q5_K_S", - "1.5b-instruct-q5_K_M", - "1.5b-instruct-q6_K", - "1.5b-instruct-q8_0", - "1.5b-instruct-fp16", - "7b-instruct", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "72b-instruct", - "72b-instruct-q2_K", - "72b-instruct-q3_K_S", - "72b-instruct-q3_K_M", - "72b-instruct-q3_K_L", - "72b-instruct-q4_0", - "72b-instruct-q4_1", - "72b-instruct-q4_K_S", - "72b-instruct-q4_K_M", - "72b-instruct-q5_0", - "72b-instruct-q5_1", - "72b-instruct-q5_K_S", - "72b-instruct-q5_K_M", - "72b-instruct-q6_K", - "72b-instruct-q8_0", - "72b-instruct-fp16" - ], - "glm4": [ - "latest", - "9b", - "9b-chat-q2_K", - "9b-chat-q3_K_S", - "9b-chat-q3_K_M", - "9b-chat-q3_K_L", - "9b-chat-q4_0", - "9b-chat-q4_1", - "9b-chat-q4_K_S", - "9b-chat-q4_K_M", - "9b-chat-q5_0", - "9b-chat-q5_1", - "9b-chat-q5_K_S", - "9b-chat-q5_K_M", - "9b-chat-q6_K", - "9b-chat-q8_0", - "9b-chat-fp16", - "9b-text-q2_K", - "9b-text-q3_K_S", - "9b-text-q3_K_M", - "9b-text-q3_K_L", - "9b-text-q4_0", - "9b-text-q4_1", - "9b-text-q4_K_S", - "9b-text-q4_K_M", - "9b-text-q5_0", - "9b-text-q5_1", - "9b-text-q5_K_S", - "9b-text-q5_K_M", - "9b-text-q6_K", - "9b-text-q8_0", - "9b-text-fp16" - ], - "aya": [ - "latest", - "8b", - "35b", - "8b-23", - "8b-23-q2_K", - "8b-23-q3_K_S", - "8b-23-q3_K_M", - "8b-23-q3_K_L", - "8b-23-q4_0", - "8b-23-q4_1", - "8b-23-q4_K_S", - "8b-23-q4_K_M", - "8b-23-q5_0", - "8b-23-q5_1", - "8b-23-q5_K_S", - "8b-23-q5_K_M", - "8b-23-q6_K", - "8b-23-q8_0", - "35b-23", - "35b-23-q2_K", - "35b-23-q3_K_S", - "35b-23-q3_K_M", - "35b-23-q3_K_L", - "35b-23-q4_0", - "35b-23-q4_1", - "35b-23-q4_K_S", - "35b-23-q4_K_M", - "35b-23-q5_0", - "35b-23-q5_1", - "35b-23-q5_K_S", - "35b-23-q5_K_M", - "35b-23-q6_K", - "35b-23-q8_0" - ], - "llama2-chinese": [ - "latest", - "7b", - "13b", - "7b-chat", - "7b-chat-q2_K", - "7b-chat-q3_K_S", - "7b-chat-q3_K_M", - "7b-chat-q3_K_L", - "7b-chat-q4_0", - "7b-chat-q4_1", - "7b-chat-q4_K_S", - "7b-chat-q4_K_M", - "7b-chat-q5_0", - "7b-chat-q5_1", - "7b-chat-q5_K_S", - "7b-chat-q5_K_M", - "7b-chat-q6_K", - "7b-chat-q8_0", - "7b-chat-fp16", - "13b-chat", - "13b-chat-q2_K", - "13b-chat-q3_K_S", - "13b-chat-q3_K_M", - "13b-chat-q3_K_L", - "13b-chat-q4_0", - "13b-chat-q4_1", - "13b-chat-q4_K_S", - "13b-chat-q4_K_M", - "13b-chat-q5_0", - "13b-chat-q5_1", - "13b-chat-q5_K_S", - "13b-chat-q5_K_M", - "13b-chat-q6_K", - "13b-chat-q8_0", - "13b-chat-fp16" - ], - "qwen3-embedding": [ - "latest", - "0.6b", - "4b", - "8b", - "0.6b-q8_0", - "0.6b-fp16", - "4b-q4_K_M", - "4b-q8_0", - "4b-fp16", - "8b-q4_K_M", - "8b-q8_0", - "8b-fp16" - ], - "stable-code": [ - "latest", - "code", - "instruct", - "3b", - "3b-code", - "3b-code-q2_K", - "3b-code-q3_K_S", - "3b-code-q3_K_M", - "3b-code-q3_K_L", - "3b-code-q4_0", - "3b-code-q4_1", - "3b-code-q4_K_S", - "3b-code-q4_K_M", - "3b-code-q5_0", - "3b-code-q5_1", - "3b-code-q5_K_S", - "3b-code-q5_K_M", - "3b-code-q6_K", - "3b-code-q8_0", - "3b-code-fp16", - "3b-instruct", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16" - ], - "neural-chat": [ - "latest", - "7b", - "7b-v3.1", - "7b-v3.1-q2_K", - "7b-v3.1-q3_K_S", - "7b-v3.1-q3_K_M", - "7b-v3.1-q3_K_L", - "7b-v3.1-q4_0", - "7b-v3.1-q4_1", - "7b-v3.1-q4_K_S", - "7b-v3.1-q4_K_M", - "7b-v3.1-q5_0", - "7b-v3.1-q5_1", - "7b-v3.1-q5_K_S", - "7b-v3.1-q5_K_M", - "7b-v3.1-q6_K", - "7b-v3.1-q8_0", - "7b-v3.1-fp16", - "7b-v3.2", - "7b-v3.2-q2_K", - "7b-v3.2-q3_K_S", - "7b-v3.2-q3_K_M", - "7b-v3.2-q3_K_L", - "7b-v3.2-q4_0", - "7b-v3.2-q4_1", - "7b-v3.2-q4_K_S", - "7b-v3.2-q4_K_M", - "7b-v3.2-q5_0", - "7b-v3.2-q5_1", - "7b-v3.2-q5_K_S", - "7b-v3.2-q5_K_M", - "7b-v3.2-q6_K", - "7b-v3.2-q8_0", - "7b-v3.2-fp16", - "7b-v3.3", - "7b-v3.3-q2_K", - "7b-v3.3-q3_K_S", - "7b-v3.3-q3_K_M", - "7b-v3.3-q3_K_L", - "7b-v3.3-q4_0", - "7b-v3.3-q4_1", - "7b-v3.3-q4_K_S", - "7b-v3.3-q4_K_M", - "7b-v3.3-q5_0", - "7b-v3.3-q5_1", - "7b-v3.3-q5_K_S", - "7b-v3.3-q5_K_M", - "7b-v3.3-q6_K", - "7b-v3.3-q8_0", - "7b-v3.3-fp16" - ], - "command-r-plus": [ - "latest", - "104b", - "104b-08-2024-q2_K", - "104b-08-2024-q3_K_S", - "104b-08-2024-q3_K_M", - "104b-08-2024-q3_K_L", - "104b-08-2024-q4_0", - "104b-08-2024-q4_1", - "104b-08-2024-q4_K_S", - "104b-08-2024-q4_K_M", - "104b-08-2024-q5_0", - "104b-08-2024-q5_1", - "104b-08-2024-q5_K_S", - "104b-08-2024-q5_K_M", - "104b-08-2024-q6_K", - "104b-08-2024-q8_0", - "104b-08-2024-fp16", - "104b-q2_K", - "104b-q4_0", - "104b-q8_0", - "104b-fp16" - ], - "nous-hermes2": [ - "latest", - "10.7b", - "34b", - "10.7b-solar-q2_K", - "10.7b-solar-q3_K_S", - "10.7b-solar-q3_K_M", - "10.7b-solar-q3_K_L", - "10.7b-solar-q4_0", - "10.7b-solar-q4_1", - "10.7b-solar-q4_K_S", - "10.7b-solar-q4_K_M", - "10.7b-solar-q5_0", - "10.7b-solar-q5_1", - "10.7b-solar-q5_K_S", - "10.7b-solar-q5_K_M", - "10.7b-solar-q6_K", - "10.7b-solar-q8_0", - "10.7b-solar-fp16", - "34b-yi-q2_K", - "34b-yi-q3_K_S", - "34b-yi-q3_K_M", - "34b-yi-q3_K_L", - "34b-yi-q4_0", - "34b-yi-q4_1", - "34b-yi-q4_K_S", - "34b-yi-q4_K_M", - "34b-yi-q5_0", - "34b-yi-q5_1", - "34b-yi-q5_K_S", - "34b-yi-q5_K_M", - "34b-yi-q6_K", - "34b-yi-q8_0", - "34b-yi-fp16" - ], - "wizardcoder": [ - "latest", - "python", - "33b", - "7b-python", - "7b-python-q2_K", - "7b-python-q3_K_S", - "7b-python-q3_K_M", - "7b-python-q3_K_L", - "7b-python-q4_0", - "7b-python-q4_1", - "7b-python-q4_K_S", - "7b-python-q4_K_M", - "7b-python-q5_0", - "7b-python-q5_1", - "7b-python-q5_K_S", - "7b-python-q5_K_M", - "7b-python-q6_K", - "7b-python-q8_0", - "7b-python-fp16", - "13b-python", - "13b-python-q2_K", - "13b-python-q3_K_S", - "13b-python-q3_K_M", - "13b-python-q3_K_L", - "13b-python-q4_0", - "13b-python-q4_1", - "13b-python-q4_K_S", - "13b-python-q4_K_M", - "13b-python-q5_0", - "13b-python-q5_1", - "13b-python-q5_K_S", - "13b-python-q5_K_M", - "13b-python-q6_K", - "13b-python-q8_0", - "13b-python-fp16", - "33b-v1.1", - "33b-v1.1-q2_K", - "33b-v1.1-q3_K_S", - "33b-v1.1-q3_K_M", - "33b-v1.1-q3_K_L", - "33b-v1.1-q4_0", - "33b-v1.1-q4_1", - "33b-v1.1-q4_K_S", - "33b-v1.1-q4_K_M", - "33b-v1.1-q5_0", - "33b-v1.1-q5_1", - "33b-v1.1-q5_K_S", - "33b-v1.1-q5_K_M", - "33b-v1.1-q6_K", - "33b-v1.1-q8_0", - "33b-v1.1-fp16", - "34b-python", - "34b-python-q2_K", - "34b-python-q3_K_S", - "34b-python-q3_K_M", - "34b-python-q3_K_L", - "34b-python-q4_0", - "34b-python-q4_1", - "34b-python-q4_K_S", - "34b-python-q4_K_M", - "34b-python-q5_0", - "34b-python-q5_1", - "34b-python-q5_K_S", - "34b-python-q5_K_M", - "34b-python-q6_K", - "34b-python-q8_0", - "34b-python-fp16" - ], - "codegeex4": [ - "latest", - "9b", - "9b-all-q2_K", - "9b-all-q3_K_S", - "9b-all-q3_K_M", - "9b-all-q3_K_L", - "9b-all-q4_0", - "9b-all-q4_1", - "9b-all-q4_K_S", - "9b-all-q4_K_M", - "9b-all-q5_0", - "9b-all-q5_1", - "9b-all-q5_K_S", - "9b-all-q5_K_M", - "9b-all-q6_K", - "9b-all-q8_0", - "9b-all-fp16" - ], - "mistral-openorca": [ - "latest", - "7b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16" - ], - "sqlcoder": [ - "latest", - "7b", - "15b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "15b-q2_K", - "15b-q3_K_S", - "15b-q3_K_M", - "15b-q3_K_L", - "15b-q4_0", - "15b-q4_1", - "15b-q4_K_S", - "15b-q4_K_M", - "15b-q5_0", - "15b-q5_1", - "15b-q5_K_S", - "15b-q5_K_M", - "15b-q6_K", - "15b-q8_0", - "15b-fp16", - "70b-alpha-q2_K", - "70b-alpha-q3_K_S", - "70b-alpha-q3_K_M", - "70b-alpha-q3_K_L", - "70b-alpha-q4_0", - "70b-alpha-q4_1", - "70b-alpha-q4_K_S", - "70b-alpha-q4_K_M", - "70b-alpha-q5_0", - "70b-alpha-q5_1", - "70b-alpha-q5_K_S", - "70b-alpha-q5_K_M", - "70b-alpha-q6_K", - "70b-alpha-q8_0", - "70b-alpha-fp16" - ], - "deepseek-v3.1": [ - "latest", - "671b", - "671b-cloud", - "671b-terminus-q4_K_M", - "671b-terminus-q8_0", - "671b-terminus-fp16", - "671b-q8_0", - "671b-fp16" - ], - "tinydolphin": [ - "latest", - "v2.8", - "1.1b", - "1.1b-v2.8-q2_K", - "1.1b-v2.8-q3_K_S", - "1.1b-v2.8-q3_K_M", - "1.1b-v2.8-q3_K_L", - "1.1b-v2.8-q4_0", - "1.1b-v2.8-q4_1", - "1.1b-v2.8-q4_K_S", - "1.1b-v2.8-q4_K_M", - "1.1b-v2.8-q5_0", - "1.1b-v2.8-q5_1", - "1.1b-v2.8-q5_K_S", - "1.1b-v2.8-q5_K_M", - "1.1b-v2.8-q6_K", - "1.1b-v2.8-q8_0", - "1.1b-v2.8-fp16" - ], - "stablelm2": [ - "latest", - "chat", - "zephyr", - "1.6b", - "12b", - "1.6b-chat", - "1.6b-chat-q2_K", - "1.6b-chat-q3_K_S", - "1.6b-chat-q3_K_M", - "1.6b-chat-q3_K_L", - "1.6b-chat-q4_0", - "1.6b-chat-q4_1", - "1.6b-chat-q4_K_S", - "1.6b-chat-q4_K_M", - "1.6b-chat-q5_0", - "1.6b-chat-q5_1", - "1.6b-chat-q5_K_S", - "1.6b-chat-q5_K_M", - "1.6b-chat-q6_K", - "1.6b-chat-q8_0", - "1.6b-chat-fp16", - "1.6b-zephyr", - "1.6b-zephyr-q2_K", - "1.6b-zephyr-q3_K_S", - "1.6b-zephyr-q3_K_M", - "1.6b-zephyr-q3_K_L", - "1.6b-zephyr-q4_0", - "1.6b-zephyr-q4_1", - "1.6b-zephyr-q4_K_S", - "1.6b-zephyr-q4_K_M", - "1.6b-zephyr-q5_0", - "1.6b-zephyr-q5_1", - "1.6b-zephyr-q5_K_S", - "1.6b-zephyr-q5_K_M", - "1.6b-zephyr-q6_K", - "1.6b-zephyr-q8_0", - "1.6b-zephyr-fp16", - "1.6b-q2_K", - "1.6b-q3_K_S", - "1.6b-q3_K_M", - "1.6b-q3_K_L", - "1.6b-q4_0", - "1.6b-q4_1", - "1.6b-q4_K_S", - "1.6b-q4_K_M", - "1.6b-q5_0", - "1.6b-q5_1", - "1.6b-q5_K_S", - "1.6b-q5_K_M", - "1.6b-q6_K", - "1.6b-q8_0", - "1.6b-fp16", - "12b-chat", - "12b-chat-q2_K", - "12b-chat-q3_K_S", - "12b-chat-q3_K_M", - "12b-chat-q3_K_L", - "12b-chat-q4_0", - "12b-chat-q4_1", - "12b-chat-q4_K_S", - "12b-chat-q4_K_M", - "12b-chat-q5_0", - "12b-chat-q5_1", - "12b-chat-q5_K_S", - "12b-chat-q5_K_M", - "12b-chat-q6_K", - "12b-chat-q8_0", - "12b-chat-fp16", - "12b-text", - "12b-q2_K", - "12b-q3_K_S", - "12b-q3_K_M", - "12b-q3_K_L", - "12b-q4_0", - "12b-q4_1", - "12b-q4_K_S", - "12b-q4_K_M", - "12b-q5_0", - "12b-q5_1", - "12b-q5_K_S", - "12b-q5_K_M", - "12b-q6_K", - "12b-q8_0", - "12b-fp16" - ], - "yi-coder": [ - "latest", - "1.5b", - "9b", - "1.5b-base", - "1.5b-base-q2_K", - "1.5b-base-q3_K_S", - "1.5b-base-q3_K_M", - "1.5b-base-q3_K_L", - "1.5b-base-q4_0", - "1.5b-base-q4_1", - "1.5b-base-q4_K_S", - "1.5b-base-q4_K_M", - "1.5b-base-q5_0", - "1.5b-base-q5_1", - "1.5b-base-q5_K_S", - "1.5b-base-q5_K_M", - "1.5b-base-q6_K", - "1.5b-base-q8_0", - "1.5b-base-fp16", - "1.5b-chat", - "1.5b-chat-q2_K", - "1.5b-chat-q3_K_S", - "1.5b-chat-q3_K_M", - "1.5b-chat-q3_K_L", - "1.5b-chat-q4_0", - "1.5b-chat-q4_1", - "1.5b-chat-q4_K_S", - "1.5b-chat-q4_K_M", - "1.5b-chat-q5_0", - "1.5b-chat-q5_1", - "1.5b-chat-q5_K_S", - "1.5b-chat-q5_K_M", - "1.5b-chat-q6_K", - "1.5b-chat-q8_0", - "1.5b-chat-fp16", - "9b-base", - "9b-base-q2_K", - "9b-base-q3_K_S", - "9b-base-q3_K_M", - "9b-base-q3_K_L", - "9b-base-q4_0", - "9b-base-q4_1", - "9b-base-q4_K_S", - "9b-base-q4_K_M", - "9b-base-q5_0", - "9b-base-q5_1", - "9b-base-q5_K_S", - "9b-base-q5_K_M", - "9b-base-q6_K", - "9b-base-q8_0", - "9b-base-fp16", - "9b-chat", - "9b-chat-q2_K", - "9b-chat-q3_K_S", - "9b-chat-q3_K_M", - "9b-chat-q3_K_L", - "9b-chat-q4_0", - "9b-chat-q4_1", - "9b-chat-q4_K_S", - "9b-chat-q4_K_M", - "9b-chat-q5_0", - "9b-chat-q5_1", - "9b-chat-q5_K_S", - "9b-chat-q5_K_M", - "9b-chat-q6_K", - "9b-chat-q8_0", - "9b-chat-fp16" - ], - "qwen3-next": [ - "latest", - "80b", - "80b-a3b-instruct-q4_K_M", - "80b-a3b-instruct-q8_0", - "80b-a3b-instruct-fp16", - "80b-a3b-thinking", - "80b-a3b-thinking-q4_K_M", - "80b-a3b-thinking-q8_0", - "80b-a3b-thinking-fp16", - "80b-cloud" - ], - "llama3-chatqa": [ - "latest", - "8b", - "70b", - "8b-v1.5", - "8b-v1.5-q2_K", - "8b-v1.5-q3_K_S", - "8b-v1.5-q3_K_M", - "8b-v1.5-q3_K_L", - "8b-v1.5-q4_0", - "8b-v1.5-q4_1", - "8b-v1.5-q4_K_S", - "8b-v1.5-q4_K_M", - "8b-v1.5-q5_0", - "8b-v1.5-q5_1", - "8b-v1.5-q5_K_S", - "8b-v1.5-q5_K_M", - "8b-v1.5-q6_K", - "8b-v1.5-q8_0", - "8b-v1.5-fp16", - "70b-v1.5", - "70b-v1.5-q2_K", - "70b-v1.5-q3_K_S", - "70b-v1.5-q3_K_M", - "70b-v1.5-q3_K_L", - "70b-v1.5-q4_0", - "70b-v1.5-q4_1", - "70b-v1.5-q4_K_S", - "70b-v1.5-q4_K_M", - "70b-v1.5-q5_0", - "70b-v1.5-q5_1", - "70b-v1.5-q5_K_S", - "70b-v1.5-q5_K_M", - "70b-v1.5-q6_K", - "70b-v1.5-q8_0", - "70b-v1.5-fp16" - ], - "granite3-dense": [ - "latest", - "2b", - "8b", - "2b-instruct-q2_K", - "2b-instruct-q3_K_S", - "2b-instruct-q3_K_M", - "2b-instruct-q3_K_L", - "2b-instruct-q4_0", - "2b-instruct-q4_1", - "2b-instruct-q4_K_S", - "2b-instruct-q4_K_M", - "2b-instruct-q5_0", - "2b-instruct-q5_1", - "2b-instruct-q5_K_S", - "2b-instruct-q5_K_M", - "2b-instruct-q6_K", - "2b-instruct-q8_0", - "2b-instruct-fp16", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-q4_0", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16" - ], - "granite3.1-dense": [ - "latest", - "2b", - "8b", - "2b-instruct-q2_K", - "2b-instruct-q3_K_S", - "2b-instruct-q3_K_M", - "2b-instruct-q3_K_L", - "2b-instruct-q4_0", - "2b-instruct-q4_1", - "2b-instruct-q4_K_S", - "2b-instruct-q4_K_M", - "2b-instruct-q5_0", - "2b-instruct-q5_1", - "2b-instruct-q5_K_S", - "2b-instruct-q5_K_M", - "2b-instruct-q6_K", - "2b-instruct-q8_0", - "2b-instruct-fp16", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-q4_0", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16" - ], - "wizard-math": [ - "latest", - "7b", - "13b", - "70b", - "7b-v1.1-q2_K", - "7b-v1.1-q3_K_S", - "7b-v1.1-q3_K_M", - "7b-v1.1-q3_K_L", - "7b-v1.1-q4_0", - "7b-v1.1-q4_1", - "7b-v1.1-q4_K_S", - "7b-v1.1-q4_K_M", - "7b-v1.1-q5_0", - "7b-v1.1-q5_1", - "7b-v1.1-q5_K_S", - "7b-v1.1-q5_K_M", - "7b-v1.1-q6_K", - "7b-v1.1-q8_0", - "7b-v1.1-fp16", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "70b-q2_K", - "70b-q3_K_S", - "70b-q3_K_M", - "70b-q3_K_L", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q4_K_M", - "70b-q5_0", - "70b-q5_1", - "70b-q5_K_S", - "70b-q5_K_M", - "70b-q6_K", - "70b-q8_0", - "70b-fp16" - ], - "dolphincoder": [ - "latest", - "7b", - "15b", - "7b-starcoder2", - "7b-starcoder2-q2_K", - "7b-starcoder2-q3_K_S", - "7b-starcoder2-q3_K_M", - "7b-starcoder2-q3_K_L", - "7b-starcoder2-q4_0", - "7b-starcoder2-q4_1", - "7b-starcoder2-q4_K_S", - "7b-starcoder2-q4_K_M", - "7b-starcoder2-q5_0", - "7b-starcoder2-q5_1", - "7b-starcoder2-q5_K_S", - "7b-starcoder2-q5_K_M", - "7b-starcoder2-q6_K", - "7b-starcoder2-q8_0", - "7b-starcoder2-fp16", - "15b-starcoder2", - "15b-starcoder2-q2_K", - "15b-starcoder2-q3_K_S", - "15b-starcoder2-q3_K_M", - "15b-starcoder2-q3_K_L", - "15b-starcoder2-q4_0", - "15b-starcoder2-q4_1", - "15b-starcoder2-q4_K_S", - "15b-starcoder2-q4_K_M", - "15b-starcoder2-q5_0", - "15b-starcoder2-q5_1", - "15b-starcoder2-q5_K_S", - "15b-starcoder2-q5_K_M", - "15b-starcoder2-q6_K", - "15b-starcoder2-q8_0", - "15b-starcoder2-fp16" - ], - "llama3-gradient": [ - "latest", - "instruct", - "1048k", - "8b", - "70b", - "8b-instruct-1048k-q2_K", - "8b-instruct-1048k-q3_K_S", - "8b-instruct-1048k-q3_K_M", - "8b-instruct-1048k-q3_K_L", - "8b-instruct-1048k-q4_0", - "8b-instruct-1048k-q4_1", - "8b-instruct-1048k-q4_K_S", - "8b-instruct-1048k-q4_K_M", - "8b-instruct-1048k-q5_0", - "8b-instruct-1048k-q5_1", - "8b-instruct-1048k-q5_K_S", - "8b-instruct-1048k-q5_K_M", - "8b-instruct-1048k-q6_K", - "8b-instruct-1048k-q8_0", - "8b-instruct-1048k-fp16", - "70b-instruct-1048k-q2_K", - "70b-instruct-1048k-q3_K_S", - "70b-instruct-1048k-q3_K_M", - "70b-instruct-1048k-q3_K_L", - "70b-instruct-1048k-q4_0", - "70b-instruct-1048k-q4_1", - "70b-instruct-1048k-q4_K_S", - "70b-instruct-1048k-q4_K_M", - "70b-instruct-1048k-q5_0", - "70b-instruct-1048k-q5_1", - "70b-instruct-1048k-q5_K_S", - "70b-instruct-1048k-q5_K_M", - "70b-instruct-1048k-q6_K", - "70b-instruct-1048k-q8_0", - "70b-instruct-1048k-fp16" - ], - "samantha-mistral": [ - "latest", - "7b", - "7b-instruct-q2_K", - "7b-instruct-q3_K_S", - "7b-instruct-q3_K_M", - "7b-instruct-q3_K_L", - "7b-instruct-q4_0", - "7b-instruct-q4_1", - "7b-instruct-q4_K_S", - "7b-instruct-q4_K_M", - "7b-instruct-q5_0", - "7b-instruct-q5_1", - "7b-instruct-q5_K_S", - "7b-instruct-q5_K_M", - "7b-instruct-q6_K", - "7b-instruct-q8_0", - "7b-instruct-fp16", - "7b-text", - "7b-text-q2_K", - "7b-text-q3_K_S", - "7b-text-q3_K_M", - "7b-text-q3_K_L", - "7b-text-q4_0", - "7b-text-q4_1", - "7b-text-q4_K_S", - "7b-text-q4_K_M", - "7b-text-q5_0", - "7b-text-q5_1", - "7b-text-q5_K_S", - "7b-text-q5_K_M", - "7b-text-q6_K", - "7b-text-q8_0", - "7b-text-fp16", - "7b-v1.2-text", - "7b-v1.2-text-q2_K", - "7b-v1.2-text-q3_K_S", - "7b-v1.2-text-q3_K_M", - "7b-v1.2-text-q3_K_L", - "7b-v1.2-text-q4_0", - "7b-v1.2-text-q4_1", - "7b-v1.2-text-q4_K_S", - "7b-v1.2-text-q4_K_M", - "7b-v1.2-text-q5_0", - "7b-v1.2-text-q5_1", - "7b-v1.2-text-q5_K_S", - "7b-v1.2-text-q5_K_M", - "7b-v1.2-text-q6_K", - "7b-v1.2-text-q8_0", - "7b-v1.2-text-fp16" - ], - "internlm2": [ - "latest", - "1m", - "1.8b", - "7b", - "20b", - "1.8b-chat-v2.5-q2_K", - "1.8b-chat-v2.5-q3_K_S", - "1.8b-chat-v2.5-q3_K_M", - "1.8b-chat-v2.5-q3_K_L", - "1.8b-chat-v2.5-q4_0", - "1.8b-chat-v2.5-q4_1", - "1.8b-chat-v2.5-q4_K_S", - "1.8b-chat-v2.5-q4_K_M", - "1.8b-chat-v2.5-q5_0", - "1.8b-chat-v2.5-q5_1", - "1.8b-chat-v2.5-q5_K_S", - "1.8b-chat-v2.5-q5_K_M", - "1.8b-chat-v2.5-q6_K", - "1.8b-chat-v2.5-q8_0", - "1.8b-chat-v2.5-fp16", - "7b-chat-1m-v2.5-q2_K", - "7b-chat-1m-v2.5-q3_K_S", - "7b-chat-1m-v2.5-q3_K_M", - "7b-chat-1m-v2.5-q3_K_L", - "7b-chat-1m-v2.5-q4_0", - "7b-chat-1m-v2.5-q4_1", - "7b-chat-1m-v2.5-q4_K_S", - "7b-chat-1m-v2.5-q4_K_M", - "7b-chat-1m-v2.5-q5_0", - "7b-chat-1m-v2.5-q5_1", - "7b-chat-1m-v2.5-q5_K_S", - "7b-chat-1m-v2.5-q5_K_M", - "7b-chat-1m-v2.5-q6_K", - "7b-chat-1m-v2.5-q8_0", - "7b-chat-1m-v2.5-fp16", - "7b-chat-v2.5-q2_K", - "7b-chat-v2.5-q3_K_S", - "7b-chat-v2.5-q3_K_M", - "7b-chat-v2.5-q3_K_L", - "7b-chat-v2.5-q4_0", - "7b-chat-v2.5-q4_1", - "7b-chat-v2.5-q4_K_S", - "7b-chat-v2.5-q4_K_M", - "7b-chat-v2.5-q5_0", - "7b-chat-v2.5-q5_1", - "7b-chat-v2.5-q5_K_S", - "7b-chat-v2.5-q5_K_M", - "7b-chat-v2.5-q6_K", - "7b-chat-v2.5-q8_0", - "7b-chat-v2.5-fp16", - "20b-chat-v2.5-q2_K", - "20b-chat-v2.5-q3_K_S", - "20b-chat-v2.5-q3_K_M", - "20b-chat-v2.5-q3_K_L", - "20b-chat-v2.5-q4_0", - "20b-chat-v2.5-q4_1", - "20b-chat-v2.5-q4_K_S", - "20b-chat-v2.5-q4_K_M", - "20b-chat-v2.5-q5_0", - "20b-chat-v2.5-q5_1", - "20b-chat-v2.5-q5_K_S", - "20b-chat-v2.5-q5_K_M", - "20b-chat-v2.5-q6_K", - "20b-chat-v2.5-q8_0", - "20b-chat-v2.5-fp16" - ], - "llama3-groq-tool-use": [ - "latest", - "8b", - "70b", - "8b-q2_K", - "8b-q3_K_S", - "8b-q3_K_M", - "8b-q3_K_L", - "8b-q4_0", - "8b-q4_1", - "8b-q4_K_S", - "8b-q4_K_M", - "8b-q5_0", - "8b-q5_1", - "8b-q5_K_S", - "8b-q5_K_M", - "8b-q6_K", - "8b-q8_0", - "8b-fp16", - "70b-q2_K", - "70b-q3_K_S", - "70b-q3_K_M", - "70b-q3_K_L", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q4_K_M", - "70b-q5_0", - "70b-q5_1", - "70b-q5_K_S", - "70b-q5_K_M", - "70b-q6_K", - "70b-q8_0", - "70b-fp16" - ], - "snowflake-arctic-embed2": [ - "latest", - "568m", - "568m-l-fp16" - ], - "starling-lm": [ - "latest", - "alpha", - "beta", - "7b", - "7b-alpha", - "7b-alpha-q2_K", - "7b-alpha-q3_K_S", - "7b-alpha-q3_K_M", - "7b-alpha-q3_K_L", - "7b-alpha-q4_0", - "7b-alpha-q4_1", - "7b-alpha-q4_K_S", - "7b-alpha-q4_K_M", - "7b-alpha-q5_0", - "7b-alpha-q5_1", - "7b-alpha-q5_K_S", - "7b-alpha-q5_K_M", - "7b-alpha-q6_K", - "7b-alpha-q8_0", - "7b-alpha-fp16", - "7b-beta", - "7b-beta-q2_K", - "7b-beta-q3_K_S", - "7b-beta-q3_K_M", - "7b-beta-q3_K_L", - "7b-beta-q4_0", - "7b-beta-q4_1", - "7b-beta-q4_K_S", - "7b-beta-q4_K_M", - "7b-beta-q5_0", - "7b-beta-q5_1", - "7b-beta-q5_K_S", - "7b-beta-q5_K_M", - "7b-beta-q6_K", - "7b-beta-q8_0", - "7b-beta-fp16" - ], - "phind-codellama": [ - "latest", - "34b", - "34b-python", - "34b-python-q2_K", - "34b-python-q3_K_S", - "34b-python-q3_K_M", - "34b-python-q3_K_L", - "34b-python-q4_0", - "34b-python-q4_1", - "34b-python-q4_K_S", - "34b-python-q4_K_M", - "34b-python-q5_0", - "34b-python-q5_1", - "34b-python-q5_K_S", - "34b-python-q5_K_M", - "34b-python-q6_K", - "34b-python-q8_0", - "34b-python-fp16", - "34b-v2", - "34b-v2-q2_K", - "34b-v2-q3_K_S", - "34b-v2-q3_K_M", - "34b-v2-q3_K_L", - "34b-v2-q4_0", - "34b-v2-q4_1", - "34b-v2-q4_K_S", - "34b-v2-q4_K_M", - "34b-v2-q5_0", - "34b-v2-q5_1", - "34b-v2-q5_K_S", - "34b-v2-q5_K_M", - "34b-v2-q6_K", - "34b-v2-q8_0", - "34b-v2-fp16", - "34b-q2_K", - "34b-q3_K_S", - "34b-q3_K_M", - "34b-q3_K_L", - "34b-q4_0", - "34b-q4_1", - "34b-q4_K_S", - "34b-q4_K_M", - "34b-q5_0", - "34b-q5_1", - "34b-q5_K_S", - "34b-q5_K_M", - "34b-q6_K", - "34b-q8_0", - "34b-fp16" - ], - "solar": [ - "latest", - "10.7b", - "10.7b-instruct-v1-q2_K", - "10.7b-instruct-v1-q3_K_S", - "10.7b-instruct-v1-q3_K_M", - "10.7b-instruct-v1-q3_K_L", - "10.7b-instruct-v1-q4_0", - "10.7b-instruct-v1-q4_1", - "10.7b-instruct-v1-q4_K_S", - "10.7b-instruct-v1-q4_K_M", - "10.7b-instruct-v1-q5_0", - "10.7b-instruct-v1-q5_1", - "10.7b-instruct-v1-q5_K_S", - "10.7b-instruct-v1-q5_K_M", - "10.7b-instruct-v1-q6_K", - "10.7b-instruct-v1-q8_0", - "10.7b-instruct-v1-fp16", - "10.7b-text-v1-q2_K", - "10.7b-text-v1-q3_K_S", - "10.7b-text-v1-q3_K_M", - "10.7b-text-v1-q3_K_L", - "10.7b-text-v1-q4_0", - "10.7b-text-v1-q4_1", - "10.7b-text-v1-q4_K_S", - "10.7b-text-v1-q4_K_M", - "10.7b-text-v1-q5_0", - "10.7b-text-v1-q5_1", - "10.7b-text-v1-q5_K_S", - "10.7b-text-v1-q5_K_M", - "10.7b-text-v1-q6_K", - "10.7b-text-v1-q8_0", - "10.7b-text-v1-fp16" - ], - "granite3.2": [ - "latest", - "2b", - "8b", - "2b-instruct-q4_K_M", - "2b-instruct-q8_0", - "2b-instruct-fp16", - "8b-instruct-q4_K_M", - "8b-instruct-q8_0", - "8b-instruct-fp16" - ], - "llama-guard3": [ - "latest", - "1b", - "8b", - "1b-q2_K", - "1b-q3_K_S", - "1b-q3_K_M", - "1b-q3_K_L", - "1b-q4_0", - "1b-q4_1", - "1b-q4_K_S", - "1b-q4_K_M", - "1b-q5_0", - "1b-q5_1", - "1b-q5_K_S", - "1b-q5_K_M", - "1b-q6_K", - "1b-q8_0", - "1b-fp16", - "8b-q2_K", - "8b-q3_K_S", - "8b-q3_K_M", - "8b-q3_K_L", - "8b-q4_0", - "8b-q4_1", - "8b-q4_K_S", - "8b-q4_K_M", - "8b-q5_0", - "8b-q5_1", - "8b-q5_K_S", - "8b-q5_K_M", - "8b-q6_K", - "8b-q8_0", - "8b-fp16" - ], - "xwinlm": [ - "latest", - "7b", - "13b", - "7b-v0.1", - "7b-v0.1-q2_K", - "7b-v0.1-q3_K_S", - "7b-v0.1-q3_K_M", - "7b-v0.1-q3_K_L", - "7b-v0.1-q4_0", - "7b-v0.1-q4_1", - "7b-v0.1-q4_K_S", - "7b-v0.1-q4_K_M", - "7b-v0.1-q5_0", - "7b-v0.1-q5_1", - "7b-v0.1-q5_K_S", - "7b-v0.1-q5_K_M", - "7b-v0.1-q6_K", - "7b-v0.1-q8_0", - "7b-v0.1-fp16", - "7b-v0.2", - "7b-v0.2-q2_K", - "7b-v0.2-q3_K_S", - "7b-v0.2-q3_K_L", - "7b-v0.2-q4_0", - "7b-v0.2-q4_1", - "7b-v0.2-q4_K_S", - "7b-v0.2-q4_K_M", - "7b-v0.2-q5_0", - "7b-v0.2-q5_K_S", - "7b-v0.2-q5_K_M", - "7b-v0.2-q6_K", - "7b-v0.2-q8_0", - "7b-v0.2-fp16", - "13b-v0.1", - "13b-v0.1-q2_K", - "13b-v0.1-q3_K_S", - "13b-v0.1-q3_K_M", - "13b-v0.1-q3_K_L", - "13b-v0.1-q4_0", - "13b-v0.1-q4_1", - "13b-v0.1-q4_K_S", - "13b-v0.1-q4_K_M", - "13b-v0.1-q5_0", - "13b-v0.1-q5_1", - "13b-v0.1-q5_K_S", - "13b-v0.1-q5_K_M", - "13b-v0.1-q6_K", - "13b-v0.1-q8_0", - "13b-v0.1-fp16", - "13b-v0.2", - "13b-v0.2-q2_K", - "13b-v0.2-q3_K_S", - "13b-v0.2-q3_K_M", - "13b-v0.2-q3_K_L", - "13b-v0.2-q4_0", - "13b-v0.2-q4_1", - "13b-v0.2-q4_K_S", - "13b-v0.2-q4_K_M", - "13b-v0.2-q5_0", - "13b-v0.2-q5_1", - "13b-v0.2-q5_K_S", - "13b-v0.2-q5_K_M", - "13b-v0.2-q6_K", - "13b-v0.2-q8_0", - "13b-v0.2-fp16", - "70b-v0.1", - "70b-v0.1-q2_K", - "70b-v0.1-q3_K_S", - "70b-v0.1-q3_K_M", - "70b-v0.1-q3_K_L", - "70b-v0.1-q4_0", - "70b-v0.1-q4_1", - "70b-v0.1-q4_K_S", - "70b-v0.1-q4_K_M", - "70b-v0.1-q5_0", - "70b-v0.1-q5_1", - "70b-v0.1-q5_K_S", - "70b-v0.1-q6_K", - "70b-v0.1-q8_0", - "70b-v0.1-fp16" - ], - "aya-expanse": [ - "latest", - "8b", - "32b", - "8b-q2_K", - "8b-q3_K_S", - "8b-q3_K_M", - "8b-q3_K_L", - "8b-q4_0", - "8b-q4_1", - "8b-q4_K_S", - "8b-q4_K_M", - "8b-q5_0", - "8b-q5_1", - "8b-q5_K_S", - "8b-q5_K_M", - "8b-q6_K", - "8b-q8_0", - "8b-fp16", - "32b-q2_K", - "32b-q3_K_S", - "32b-q3_K_M", - "32b-q3_K_L", - "32b-q4_0", - "32b-q4_1", - "32b-q4_K_S", - "32b-q4_K_M", - "32b-q5_0", - "32b-q5_1", - "32b-q5_K_S", - "32b-q5_K_M", - "32b-q6_K", - "32b-q8_0", - "32b-fp16" - ], - "yarn-llama2": [ - "latest", - "7b", - "13b", - "7b-128k", - "7b-128k-q2_K", - "7b-128k-q3_K_S", - "7b-128k-q3_K_M", - "7b-128k-q3_K_L", - "7b-128k-q4_0", - "7b-128k-q4_1", - "7b-128k-q4_K_S", - "7b-128k-q4_K_M", - "7b-128k-q5_0", - "7b-128k-q5_1", - "7b-128k-q5_K_S", - "7b-128k-q5_K_M", - "7b-128k-q6_K", - "7b-128k-q8_0", - "7b-128k-fp16", - "7b-64k", - "7b-64k-q2_K", - "7b-64k-q3_K_S", - "7b-64k-q3_K_M", - "7b-64k-q3_K_L", - "7b-64k-q4_0", - "7b-64k-q4_1", - "7b-64k-q4_K_S", - "7b-64k-q4_K_M", - "7b-64k-q5_0", - "7b-64k-q5_1", - "7b-64k-q5_K_S", - "7b-64k-q5_K_M", - "7b-64k-q6_K", - "7b-64k-q8_0", - "7b-64k-fp16", - "13b-128k", - "13b-128k-q2_K", - "13b-128k-q3_K_S", - "13b-128k-q3_K_M", - "13b-128k-q3_K_L", - "13b-128k-q4_0", - "13b-128k-q4_1", - "13b-128k-q4_K_S", - "13b-128k-q4_K_M", - "13b-128k-q5_0", - "13b-128k-q5_1", - "13b-128k-q5_K_S", - "13b-128k-q5_K_M", - "13b-128k-q6_K", - "13b-128k-q8_0", - "13b-128k-fp16", - "13b-64k", - "13b-64k-q2_K", - "13b-64k-q3_K_S", - "13b-64k-q3_K_M", - "13b-64k-q3_K_L", - "13b-64k-q4_0", - "13b-64k-q4_1", - "13b-64k-q4_K_S", - "13b-64k-q4_K_M", - "13b-64k-q5_0", - "13b-64k-q5_1", - "13b-64k-q5_K_S", - "13b-64k-q5_K_M", - "13b-64k-q6_K", - "13b-64k-q8_0", - "13b-64k-fp16" - ], - "granite3-moe": [ - "latest", - "1b", - "3b", - "1b-instruct-q2_K", - "1b-instruct-q3_K_S", - "1b-instruct-q3_K_M", - "1b-instruct-q3_K_L", - "1b-instruct-q4_0", - "1b-instruct-q4_1", - "1b-instruct-q4_K_S", - "1b-instruct-q4_K_M", - "1b-instruct-q5_0", - "1b-instruct-q5_1", - "1b-instruct-q5_K_S", - "1b-instruct-q5_K_M", - "1b-instruct-q6_K", - "1b-instruct-q8_0", - "1b-instruct-fp16", - "3b-instruct-q2_K", - "3b-instruct-q3_K_S", - "3b-instruct-q3_K_M", - "3b-instruct-q3_K_L", - "3b-instruct-q4_0", - "3b-instruct-q4_1", - "3b-instruct-q4_K_S", - "3b-instruct-q4_K_M", - "3b-instruct-q5_0", - "3b-instruct-q5_1", - "3b-instruct-q5_K_S", - "3b-instruct-q5_K_M", - "3b-instruct-q6_K", - "3b-instruct-q8_0", - "3b-instruct-fp16" - ], - "reflection": [ - "latest", - "70b", - "70b-q2_K", - "70b-q3_K_S", - "70b-q3_K_M", - "70b-q3_K_L", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q4_K_M", - "70b-q5_0", - "70b-q5_1", - "70b-q5_K_S", - "70b-q5_K_M", - "70b-q6_K", - "70b-q8_0", - "70b-fp16" - ], - "orca2": [ - "latest", - "7b", - "13b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16" - ], - "r1-1776": [ - "latest", - "70b", - "671b", - "70b-distill-llama-q4_K_M", - "70b-distill-llama-q8_0", - "70b-distill-llama-fp16", - "671b-q4_K_M", - "671b-q8_0", - "671b-fp16" - ], - "exaone3.5": [ - "latest", - "2.4b", - "7.8b", - "32b", - "2.4b-instruct-q4_K_M", - "2.4b-instruct-q8_0", - "2.4b-instruct-fp16", - "7.8b-instruct-q4_K_M", - "7.8b-instruct-q8_0", - "7.8b-instruct-fp16", - "32b-instruct-q4_K_M", - "32b-instruct-q8_0", - "32b-instruct-fp16" - ], - "stable-beluga": [ - "latest", - "7b", - "13b", - "70b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "70b-q2_K", - "70b-q3_K_S", - "70b-q3_K_M", - "70b-q3_K_L", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q4_K_M", - "70b-q5_0", - "70b-q5_1", - "70b-q5_K_S", - "70b-q5_K_M", - "70b-q6_K", - "70b-q8_0", - "70b-fp16" - ], - "nemotron-mini": [ - "latest", - "4b", - "4b-instruct-q2_K", - "4b-instruct-q3_K_S", - "4b-instruct-q3_K_M", - "4b-instruct-q3_K_L", - "4b-instruct-q4_0", - "4b-instruct-q4_1", - "4b-instruct-q4_K_S", - "4b-instruct-q4_K_M", - "4b-instruct-q5_0", - "4b-instruct-q5_1", - "4b-instruct-q5_K_S", - "4b-instruct-q5_K_M", - "4b-instruct-q6_K", - "4b-instruct-q8_0", - "4b-instruct-fp16" - ], - "meditron": [ - "latest", - "7b", - "70b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q5_1" - ], - "reader-lm": [ - "latest", - "0.5b", - "1.5b", - "0.5b-q2_K", - "0.5b-q3_K_S", - "0.5b-q3_K_M", - "0.5b-q3_K_L", - "0.5b-q4_0", - "0.5b-q4_1", - "0.5b-q4_K_S", - "0.5b-q4_K_M", - "0.5b-q5_0", - "0.5b-q5_1", - "0.5b-q5_K_S", - "0.5b-q5_K_M", - "0.5b-q6_K", - "0.5b-q8_0", - "0.5b-fp16", - "1.5b-q2_K", - "1.5b-q3_K_S", - "1.5b-q3_K_M", - "1.5b-q3_K_L", - "1.5b-q4_0", - "1.5b-q4_1", - "1.5b-q4_K_S", - "1.5b-q4_K_M", - "1.5b-q5_0", - "1.5b-q5_1", - "1.5b-q5_K_S", - "1.5b-q5_K_M", - "1.5b-q6_K", - "1.5b-q8_0", - "1.5b-fp16" - ], - "shieldgemma": [ - "latest", - "2b", - "9b", - "27b", - "2b-q2_K", - "2b-q3_K_S", - "2b-q3_K_M", - "2b-q3_K_L", - "2b-q4_0", - "2b-q4_1", - "2b-q4_K_S", - "2b-q4_K_M", - "2b-q5_0", - "2b-q5_1", - "2b-q5_K_S", - "2b-q5_K_M", - "2b-q6_K", - "2b-q8_0", - "2b-fp16", - "9b-q2_K", - "9b-q3_K_S", - "9b-q3_K_M", - "9b-q3_K_L", - "9b-q4_0", - "9b-q4_1", - "9b-q4_K_S", - "9b-q4_K_M", - "9b-q5_0", - "9b-q5_1", - "9b-q5_K_S", - "9b-q5_K_M", - "9b-q6_K", - "9b-q8_0", - "9b-fp16", - "27b-q2_K", - "27b-q3_K_S", - "27b-q3_K_M", - "27b-q3_K_L", - "27b-q4_0", - "27b-q4_1", - "27b-q4_K_S", - "27b-q4_K_M", - "27b-q5_0", - "27b-q5_1", - "27b-q5_K_S", - "27b-q5_K_M", - "27b-q6_K", - "27b-q8_0", - "27b-fp16" - ], - "athene-v2": [ - "latest", - "72b", - "72b-q2_K", - "72b-q3_K_S", - "72b-q3_K_M", - "72b-q3_K_L", - "72b-q4_0", - "72b-q4_1", - "72b-q4_K_S", - "72b-q4_K_M", - "72b-q5_0", - "72b-q5_1", - "72b-q5_K_S", - "72b-q5_K_M", - "72b-q6_K", - "72b-q8_0", - "72b-fp16" - ], - "llama-pro": [ - "latest", - "instruct", - "text", - "8b-instruct-q2_K", - "8b-instruct-q3_K_S", - "8b-instruct-q3_K_M", - "8b-instruct-q3_K_L", - "8b-instruct-q4_0", - "8b-instruct-q4_1", - "8b-instruct-q4_K_S", - "8b-instruct-q4_K_M", - "8b-instruct-q5_0", - "8b-instruct-q5_1", - "8b-instruct-q5_K_S", - "8b-instruct-q5_K_M", - "8b-instruct-q6_K", - "8b-instruct-q8_0", - "8b-instruct-fp16", - "8b-text-q2_K", - "8b-text-q3_K_S", - "8b-text-q3_K_M", - "8b-text-q3_K_L", - "8b-text-q4_0", - "8b-text-q4_1", - "8b-text-q4_K_S", - "8b-text-q4_K_M", - "8b-text-q5_0", - "8b-text-q5_1", - "8b-text-q5_K_S", - "8b-text-q5_K_M", - "8b-text-q6_K", - "8b-text-q8_0", - "8b-text-fp16" - ], - "bge-large": [ - "latest", - "335m", - "335m-en-v1.5-fp16" - ], - "nemotron": [ - "latest", - "70b", - "70b-instruct-q2_K", - "70b-instruct-q3_K_S", - "70b-instruct-q3_K_M", - "70b-instruct-q3_K_L", - "70b-instruct-q4_0", - "70b-instruct-q4_1", - "70b-instruct-q4_K_S", - "70b-instruct-q4_K_M", - "70b-instruct-q5_0", - "70b-instruct-q5_1", - "70b-instruct-q5_K_S", - "70b-instruct-q5_K_M", - "70b-instruct-q6_K", - "70b-instruct-q8_0", - "70b-instruct-fp16" - ], - "yarn-mistral": [ - "latest", - "7b", - "7b-128k", - "7b-128k-q2_K", - "7b-128k-q3_K_S", - "7b-128k-q3_K_M", - "7b-128k-q3_K_L", - "7b-128k-q4_0", - "7b-128k-q4_1", - "7b-128k-q4_K_S", - "7b-128k-q4_K_M", - "7b-128k-q5_0", - "7b-128k-q5_1", - "7b-128k-q5_K_S", - "7b-128k-q5_K_M", - "7b-128k-q6_K", - "7b-128k-q8_0", - "7b-128k-fp16", - "7b-64k", - "7b-64k-q2_K", - "7b-64k-q3_K_S", - "7b-64k-q3_K_M", - "7b-64k-q3_K_L", - "7b-64k-q4_0", - "7b-64k-q4_1", - "7b-64k-q4_K_S", - "7b-64k-q4_K_M", - "7b-64k-q5_0", - "7b-64k-q5_1", - "7b-64k-q5_K_S", - "7b-64k-q5_K_M", - "7b-64k-q6_K", - "7b-64k-q8_0" - ], - "wizardlm-uncensored": [ - "latest", - "13b", - "13b-llama2", - "13b-llama2-q2_K", - "13b-llama2-q3_K_S", - "13b-llama2-q3_K_M", - "13b-llama2-q3_K_L", - "13b-llama2-q4_0", - "13b-llama2-q4_1", - "13b-llama2-q4_K_S", - "13b-llama2-q4_K_M", - "13b-llama2-q5_0", - "13b-llama2-q5_1", - "13b-llama2-q5_K_S", - "13b-llama2-q5_K_M", - "13b-llama2-q6_K", - "13b-llama2-q8_0", - "13b-llama2-fp16" - ], - "nexusraven": [ - "latest", - "13b", - "13b-v2-q2_K", - "13b-v2-q3_K_S", - "13b-v2-q3_K_M", - "13b-v2-q3_K_L", - "13b-v2-q4_0", - "13b-v2-q4_1", - "13b-v2-q4_K_S", - "13b-v2-q4_K_M", - "13b-v2-q5_0", - "13b-v2-q5_1", - "13b-v2-q5_K_S", - "13b-v2-q5_K_M", - "13b-v2-q6_K", - "13b-v2-q8_0", - "13b-v2-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16" - ], - "wizardlm": [ - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16", - "13b-llama2-q2_K", - "13b-llama2-q3_K_S", - "13b-llama2-q3_K_M", - "13b-llama2-q3_K_L", - "13b-llama2-q4_0", - "13b-llama2-q4_1", - "13b-llama2-q4_K_S", - "13b-llama2-q4_K_M", - "13b-llama2-q5_0", - "13b-llama2-q5_1", - "13b-llama2-q5_K_S", - "13b-llama2-q5_K_M", - "13b-llama2-q6_K", - "13b-llama2-q8_0", - "13b-llama2-fp16", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16", - "30b-q2_K", - "30b-q3_K_S", - "30b-q3_K_M", - "30b-q3_K_L", - "30b-q4_0", - "30b-q4_1", - "30b-q4_K_S", - "30b-q4_K_M", - "30b-q5_0", - "30b-q5_1", - "30b-q5_K_S", - "30b-q5_K_M", - "30b-q6_K", - "30b-q8_0", - "30b-fp16", - "70b-llama2-q2_K", - "70b-llama2-q3_K_S", - "70b-llama2-q3_K_M", - "70b-llama2-q3_K_L", - "70b-llama2-q4_0", - "70b-llama2-q4_1", - "70b-llama2-q4_K_S", - "70b-llama2-q4_K_M", - "70b-llama2-q5_0", - "70b-llama2-q5_K_S", - "70b-llama2-q5_K_M", - "70b-llama2-q6_K", - "70b-llama2-q8_0" - ], - "llava-phi3": [ - "latest", - "3.8b", - "3.8b-mini-q4_0", - "3.8b-mini-fp16" - ], - "granite-embedding": [ - "latest", - "30m", - "278m", - "30m-en", - "30m-en-fp16", - "278m-fp16" - ], - "tulu3": [ - "latest", - "8b", - "70b", - "8b-q4_K_M", - "8b-q8_0", - "8b-fp16", - "70b-q4_K_M", - "70b-q8_0", - "70b-fp16" - ], - "medllama2": [ - "latest", - "7b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16" - ], - "nous-hermes2-mixtral": [ - "latest", - "dpo", - "8x7b", - "8x7b-dpo-q2_K", - "8x7b-dpo-q3_K_S", - "8x7b-dpo-q3_K_M", - "8x7b-dpo-q3_K_L", - "8x7b-dpo-q4_0", - "8x7b-dpo-q4_1", - "8x7b-dpo-q4_K_S", - "8x7b-dpo-q4_K_M", - "8x7b-dpo-q5_0", - "8x7b-dpo-q5_1", - "8x7b-dpo-q5_K_S", - "8x7b-dpo-q5_K_M", - "8x7b-dpo-q6_K", - "8x7b-dpo-q8_0", - "8x7b-dpo-fp16" - ], - "dbrx": [ - "latest", - "instruct", - "132b", - "132b-instruct-q2_K", - "132b-instruct-q4_0", - "132b-instruct-q8_0", - "132b-instruct-fp16" - ], - "codeup": [ - "latest", - "13b", - "13b-llama2", - "13b-llama2-chat", - "13b-llama2-chat-q2_K", - "13b-llama2-chat-q3_K_S", - "13b-llama2-chat-q3_K_M", - "13b-llama2-chat-q3_K_L", - "13b-llama2-chat-q4_0", - "13b-llama2-chat-q4_1", - "13b-llama2-chat-q4_K_S", - "13b-llama2-chat-q4_K_M", - "13b-llama2-chat-q5_0", - "13b-llama2-chat-q5_1", - "13b-llama2-chat-q5_K_S", - "13b-llama2-chat-q5_K_M", - "13b-llama2-chat-q6_K", - "13b-llama2-chat-q8_0", - "13b-llama2-chat-fp16" - ], - "everythinglm": [ - "latest", - "13b", - "13b-16k", - "13b-16k-q2_K", - "13b-16k-q3_K_S", - "13b-16k-q3_K_M", - "13b-16k-q3_K_L", - "13b-16k-q4_0", - "13b-16k-q4_1", - "13b-16k-q4_K_S", - "13b-16k-q4_K_M", - "13b-16k-q5_0", - "13b-16k-q5_1", - "13b-16k-q5_K_S", - "13b-16k-q5_K_M", - "13b-16k-q6_K", - "13b-16k-q8_0", - "13b-16k-fp16" - ], - "mathstral": [ - "latest", - "7b", - "7b-v0.1-q2_K", - "7b-v0.1-q3_K_S", - "7b-v0.1-q3_K_M", - "7b-v0.1-q3_K_L", - "7b-v0.1-q4_0", - "7b-v0.1-q4_1", - "7b-v0.1-q4_K_S", - "7b-v0.1-q4_K_M", - "7b-v0.1-q5_0", - "7b-v0.1-q5_1", - "7b-v0.1-q5_K_S", - "7b-v0.1-q5_K_M", - "7b-v0.1-q6_K", - "7b-v0.1-q8_0", - "7b-v0.1-fp16" - ], - "solar-pro": [ - "latest", - "preview", - "22b", - "22b-preview-instruct-q2_K", - "22b-preview-instruct-q3_K_S", - "22b-preview-instruct-q3_K_M", - "22b-preview-instruct-q3_K_L", - "22b-preview-instruct-q4_0", - "22b-preview-instruct-q4_1", - "22b-preview-instruct-q4_K_S", - "22b-preview-instruct-q4_K_M", - "22b-preview-instruct-q5_0", - "22b-preview-instruct-q5_1", - "22b-preview-instruct-q5_K_S", - "22b-preview-instruct-q5_K_M", - "22b-preview-instruct-q6_K", - "22b-preview-instruct-q8_0", - "22b-preview-instruct-fp16" - ], - "stablelm-zephyr": [ - "latest", - "3b", - "3b-q2_K", - "3b-q3_K_S", - "3b-q3_K_M", - "3b-q3_K_L", - "3b-q4_0", - "3b-q4_1", - "3b-q4_K_S", - "3b-q4_K_M", - "3b-q5_0", - "3b-q5_1", - "3b-q5_K_S", - "3b-q5_K_M", - "3b-q6_K", - "3b-q8_0", - "3b-fp16" - ], - "falcon2": [ - "latest", - "11b", - "11b-q2_K", - "11b-q3_K_S", - "11b-q3_K_M", - "11b-q3_K_L", - "11b-q4_0", - "11b-q4_1", - "11b-q4_K_S", - "11b-q4_K_M", - "11b-q5_0", - "11b-q5_1", - "11b-q5_K_S", - "11b-q5_K_M", - "11b-q6_K", - "11b-q8_0", - "11b-fp16" - ], - "magicoder": [ - "latest", - "7b", - "7b-s-cl", - "7b-s-cl-q2_K", - "7b-s-cl-q3_K_S", - "7b-s-cl-q3_K_M", - "7b-s-cl-q3_K_L", - "7b-s-cl-q4_0", - "7b-s-cl-q4_1", - "7b-s-cl-q4_K_S", - "7b-s-cl-q4_K_M", - "7b-s-cl-q5_0", - "7b-s-cl-q5_1", - "7b-s-cl-q5_K_S", - "7b-s-cl-q5_K_M", - "7b-s-cl-q6_K", - "7b-s-cl-q8_0", - "7b-s-cl-fp16" - ], - "smallthinker": [ - "latest", - "3b", - "3b-preview-q4_K_M", - "3b-preview-q8_0", - "3b-preview-fp16" - ], - "duckdb-nsql": [ - "latest", - "7b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16" - ], - "mistrallite": [ - "latest", - "7b", - "7b-v0.1-q2_K", - "7b-v0.1-q3_K_S", - "7b-v0.1-q3_K_M", - "7b-v0.1-q3_K_L", - "7b-v0.1-q4_0", - "7b-v0.1-q4_1", - "7b-v0.1-q4_K_S", - "7b-v0.1-q4_K_M", - "7b-v0.1-q5_0", - "7b-v0.1-q5_1", - "7b-v0.1-q5_K_S", - "7b-v0.1-q5_K_M", - "7b-v0.1-q6_K", - "7b-v0.1-q8_0", - "7b-v0.1-fp16" - ], - "nuextract": [ - "latest", - "3.8b", - "3.8b-q2_K", - "3.8b-q3_K_S", - "3.8b-q3_K_M", - "3.8b-q3_K_L", - "3.8b-q4_0", - "3.8b-q4_1", - "3.8b-q4_K_S", - "3.8b-q4_K_M", - "3.8b-q5_0", - "3.8b-q5_1", - "3.8b-q5_K_S", - "3.8b-q5_K_M", - "3.8b-q6_K", - "3.8b-q8_0", - "3.8b-fp16" - ], - "bespoke-minicheck": [ - "latest", - "7b", - "7b-q2_K", - "7b-q3_K_S", - "7b-q3_K_M", - "7b-q3_K_L", - "7b-q4_0", - "7b-q4_1", - "7b-q4_K_S", - "7b-q4_K_M", - "7b-q5_0", - "7b-q5_1", - "7b-q5_K_S", - "7b-q5_K_M", - "7b-q6_K", - "7b-q8_0", - "7b-fp16" - ], - "codebooga": [ - "latest", - "34b", - "34b-v0.1-q2_K", - "34b-v0.1-q3_K_S", - "34b-v0.1-q3_K_M", - "34b-v0.1-q3_K_L", - "34b-v0.1-q4_0", - "34b-v0.1-q4_1", - "34b-v0.1-q4_K_M", - "34b-v0.1-q5_0", - "34b-v0.1-q5_1", - "34b-v0.1-q5_K_S", - "34b-v0.1-q5_K_M", - "34b-v0.1-q6_K", - "34b-v0.1-q8_0", - "34b-v0.1-fp16" - ], - "megadolphin": [ - "latest", - "v2.2", - "120b", - "120b-v2.2", - "120b-v2.2-q2_K", - "120b-v2.2-q3_K_S", - "120b-v2.2-q3_K_M", - "120b-v2.2-q3_K_L", - "120b-v2.2-q4_0", - "120b-v2.2-q4_1", - "120b-v2.2-q4_K_S", - "120b-v2.2-q4_K_M", - "120b-v2.2-q5_0", - "120b-v2.2-q5_1", - "120b-v2.2-q5_K_S", - "120b-v2.2-q5_K_M", - "120b-v2.2-q6_K", - "120b-v2.2-q8_0", - "120b-v2.2-fp16" - ], - "wizard-vicuna": [ - "latest", - "13b", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16" - ], - "command-r7b": [ - "latest", - "7b", - "7b-12-2024-q4_K_M", - "7b-12-2024-q8_0", - "7b-12-2024-fp16" - ], - "phi4-mini-reasoning": [ - "latest", - "3.8b", - "3.8b-q4_K_M", - "3.8b-q8_0", - "3.8b-fp16" - ], - "deepseek-v2.5": [ - "latest", - "236b", - "236b-q4_0", - "236b-q4_1", - "236b-q5_0", - "236b-q5_1", - "236b-q8_0" - ], - "notux": [ - "latest", - "8x7b", - "8x7b-v1", - "8x7b-v1-q2_K", - "8x7b-v1-q3_K_S", - "8x7b-v1-q3_K_M", - "8x7b-v1-q3_K_L", - "8x7b-v1-q4_0", - "8x7b-v1-q4_1", - "8x7b-v1-q4_K_S", - "8x7b-v1-q4_K_M", - "8x7b-v1-q5_0", - "8x7b-v1-q5_1", - "8x7b-v1-q5_K_S", - "8x7b-v1-q5_K_M", - "8x7b-v1-q6_K", - "8x7b-v1-q8_0", - "8x7b-v1-fp16" - ], - "notus": [ - "latest", - "7b", - "7b-v1", - "7b-v1-q2_K", - "7b-v1-q3_K_S", - "7b-v1-q3_K_M", - "7b-v1-q3_K_L", - "7b-v1-q4_0", - "7b-v1-q4_1", - "7b-v1-q4_K_S", - "7b-v1-q4_K_M", - "7b-v1-q5_0", - "7b-v1-q5_1", - "7b-v1-q5_K_S", - "7b-v1-q5_K_M", - "7b-v1-q6_K", - "7b-v1-q8_0", - "7b-v1-fp16" - ], - "firefunction-v2": [ - "latest", - "70b", - "70b-q2_K", - "70b-q3_K_S", - "70b-q3_K_M", - "70b-q3_K_L", - "70b-q4_0", - "70b-q4_1", - "70b-q4_K_S", - "70b-q4_K_M", - "70b-q5_0", - "70b-q5_1", - "70b-q5_K_S", - "70b-q5_K_M", - "70b-q6_K", - "70b-q8_0", - "70b-fp16" - ], - "open-orca-platypus2": [ - "latest", - "13b", - "13b-q2_K", - "13b-q3_K_S", - "13b-q3_K_M", - "13b-q3_K_L", - "13b-q4_0", - "13b-q4_1", - "13b-q4_K_S", - "13b-q4_K_M", - "13b-q5_0", - "13b-q5_1", - "13b-q5_K_S", - "13b-q5_K_M", - "13b-q6_K", - "13b-q8_0", - "13b-fp16" - ], - "goliath": [ - "latest", - "120b-q2_K", - "120b-q3_K_S", - "120b-q3_K_M", - "120b-q3_K_L", - "120b-q4_0", - "120b-q4_1", - "120b-q4_K_S", - "120b-q4_K_M", - "120b-q5_0", - "120b-q5_1", - "120b-q5_K_S", - "120b-q5_K_M", - "120b-q6_K", - "120b-q8_0", - "120b-fp16" - ], - "command-a": [ - "latest", - "111b", - "111b-03-2025-q4_K_M", - "111b-03-2025-q8_0", - "111b-03-2025-fp16" - ], - "deepseek-ocr": [ - "latest", - "3b", - "3b-bf16" - ], - "sailor2": [ - "latest", - "1b", - "8b", - "20b", - "1b-chat-q4_K_M", - "1b-chat-q8_0", - "1b-chat-fp16", - "8b-chat-q4_K_M", - "8b-chat-q8_0", - "8b-chat-fp16", - "20b-chat-q4_K_M", - "20b-chat-q8_0", - "20b-chat-fp16" - ], - "granite3-guardian": [ - "latest", - "2b", - "8b", - "2b-q8_0", - "2b-fp16", - "8b-q5_K_S", - "8b-q5_K_M", - "8b-q6_K", - "8b-q8_0", - "8b-fp16" - ], - "marco-o1": [ - "latest", - "7b", - "7b-q4_K_M", - "7b-q8_0", - "7b-fp16" - ], - "gemini-3-pro-preview": [ - "latest" - ], - "alfred": [ - "latest", - "40b", - "40b-1023-q4_0", - "40b-1023-q4_1", - "40b-1023-q5_0", - "40b-1023-q5_1", - "40b-1023-q8_0" - ], - "command-r7b-arabic": [ - "latest", - "7b", - "7b-02-2025-q4_K_M", - "7b-02-2025-q8_0", - "7b-02-2025-fp16" - ], - "gpt-oss-safeguard": [ - "latest", - "20b", - "120b" - ], - "glm-4.6": [ - "cloud" - ], - "olmo-3.1": [ - "latest", - "32b", - "32b-instruct", - "32b-instruct-q4_K_M", - "32b-instruct-q8_0", - "32b-instruct-fp16", - "32b-think", - "32b-think-q4_K_M", - "32b-think-q8_0", - "32b-think-fp16" - ], - "cogito-2.1": [ - "latest", - "671b", - "671b-cloud", - "671b-q4_K_M", - "671b-q8_0", - "671b-fp16" - ], - "minimax-m2": [ - "cloud" - ], - "rnj-1": [ - "latest", - "8b", - "8b-cloud", - "8b-instruct-q4_K_M", - "8b-instruct-q8_0", - "8b-instruct-fp16" - ], - "kimi-k2": [ - "1t-cloud" - ], - "kimi-k2-thinking": [ - "cloud" - ], - "nomic-embed-text-v2-moe": [ - "latest" - ], - "deepseek-v3.2": [ - "cloud" - ], - "glm-4.7": [ - "cloud" - ], - "mistral-large-3": [ - "675b-cloud" - ], - "minimax-m2.1": [ - "cloud" - ] + "nemotron-3-nano": { + "tags": [ + "latest", + "30b", + "30b-a3b-q4_K_M", + "30b-a3b-q8_0", + "30b-a3b-fp16", + "30b-cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "functiongemma": { + "tags": [ + "latest", + "270m", + "270m-it-q8_0", + "270m-it-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "olmo-3": { + "tags": [ + "latest", + "7b", + "32b", + "7b-instruct", + "7b-instruct-q4_K_M", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "7b-think", + "7b-think-q4_K_M", + "7b-think-q8_0", + "7b-think-fp16", + "32b-think", + "32b-think-q4_K_M", + "32b-think-q8_0", + "32b-think-fp16" + ], + "capabilities": [] + }, + "gemini-3-flash-preview": { + "tags": [ + "latest", + "cloud" + ], + "capabilities": [ + "vision", + "tools", + "thinking" + ] + }, + "devstral-small-2": { + "tags": [ + "latest", + "24b", + "24b-cloud", + "24b-instruct-2512-q4_K_M", + "24b-instruct-2512-q8_0", + "24b-instruct-2512-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "devstral-2": { + "tags": [ + "latest", + "123b", + "123b-cloud", + "123b-instruct-2512-q4_K_M", + "123b-instruct-2512-q8_0", + "123b-instruct-2512-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "ministral-3": { + "tags": [ + "latest", + "3b", + "8b", + "14b", + "3b-cloud", + "3b-instruct-2512-q4_K_M", + "3b-instruct-2512-q8_0", + "3b-instruct-2512-fp16", + "8b-cloud", + "8b-instruct-2512-q4_K_M", + "8b-instruct-2512-q8_0", + "8b-instruct-2512-fp16", + "14b-cloud", + "14b-instruct-2512-q4_K_M", + "14b-instruct-2512-q8_0", + "14b-instruct-2512-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "qwen3-vl": { + "tags": [ + "latest", + "2b", + "4b", + "8b", + "30b", + "32b", + "235b", + "2b-instruct", + "2b-instruct-q4_K_M", + "2b-instruct-q8_0", + "2b-instruct-bf16", + "2b-thinking", + "2b-thinking-q4_K_M", + "2b-thinking-q8_0", + "2b-thinking-bf16", + "4b-instruct", + "4b-instruct-q4_K_M", + "4b-instruct-q8_0", + "4b-instruct-bf16", + "4b-thinking", + "4b-thinking-q4_K_M", + "4b-thinking-q8_0", + "4b-thinking-bf16", + "8b-instruct", + "8b-instruct-q4_K_M", + "8b-instruct-q8_0", + "8b-instruct-bf16", + "8b-thinking", + "8b-thinking-q4_K_M", + "8b-thinking-q8_0", + "8b-thinking-bf16", + "30b-a3b", + "30b-a3b-instruct", + "30b-a3b-instruct-q4_K_M", + "30b-a3b-instruct-q8_0", + "30b-a3b-instruct-bf16", + "30b-a3b-thinking", + "30b-a3b-thinking-q4_K_M", + "30b-a3b-thinking-q8_0", + "30b-a3b-thinking-bf16", + "32b-instruct", + "32b-instruct-q4_K_M", + "32b-instruct-q8_0", + "32b-instruct-bf16", + "32b-thinking", + "32b-thinking-q4_K_M", + "32b-thinking-q8_0", + "32b-thinking-bf16", + "235b-a22b", + "235b-a22b-instruct", + "235b-a22b-instruct-q4_K_M", + "235b-a22b-instruct-q8_0", + "235b-a22b-instruct-bf16", + "235b-a22b-thinking", + "235b-a22b-thinking-q4_K_M", + "235b-a22b-thinking-q8_0", + "235b-a22b-thinking-bf16", + "235b-cloud", + "235b-instruct-cloud" + ], + "capabilities": [ + "vision", + "tools", + "thinking" + ] + }, + "gpt-oss": { + "tags": [ + "latest", + "20b", + "120b", + "20b-cloud", + "120b-cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "deepseek-r1": { + "tags": [ + "latest", + "1.5b", + "7b", + "8b", + "14b", + "32b", + "70b", + "671b", + "1.5b-qwen-distill-q4_K_M", + "1.5b-qwen-distill-q8_0", + "1.5b-qwen-distill-fp16", + "7b-qwen-distill-q4_K_M", + "7b-qwen-distill-q8_0", + "7b-qwen-distill-fp16", + "8b-0528-qwen3-q4_K_M", + "8b-0528-qwen3-q8_0", + "8b-0528-qwen3-fp16", + "8b-llama-distill-q4_K_M", + "8b-llama-distill-q8_0", + "8b-llama-distill-fp16", + "14b-qwen-distill-q4_K_M", + "14b-qwen-distill-q8_0", + "14b-qwen-distill-fp16", + "32b-qwen-distill-q4_K_M", + "32b-qwen-distill-q8_0", + "32b-qwen-distill-fp16", + "70b-llama-distill-q4_K_M", + "70b-llama-distill-q8_0", + "70b-llama-distill-fp16", + "671b-0528-q4_K_M", + "671b-0528-q8_0", + "671b-0528-fp16", + "671b-q4_K_M", + "671b-q8_0", + "671b-fp16" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "qwen3-coder": { + "tags": [ + "latest", + "30b", + "480b", + "30b-a3b-q4_K_M", + "30b-a3b-q8_0", + "30b-a3b-fp16", + "480b-a35b-q4_K_M", + "480b-a35b-q8_0", + "480b-a35b-fp16", + "480b-cloud" + ], + "capabilities": [ + "tools" + ] + }, + "gemma3": { + "tags": [ + "latest", + "270m", + "1b", + "4b", + "12b", + "27b", + "270m-it-qat", + "270m-it-q8_0", + "270m-it-fp16", + "270m-it-bf16", + "1b-it-qat", + "1b-it-q4_K_M", + "1b-it-q8_0", + "1b-it-fp16", + "4b-cloud", + "4b-it-qat", + "4b-it-q4_K_M", + "4b-it-q8_0", + "4b-it-fp16", + "12b-cloud", + "12b-it-qat", + "12b-it-q4_K_M", + "12b-it-q8_0", + "12b-it-fp16", + "27b-cloud", + "27b-it-qat", + "27b-it-q4_K_M", + "27b-it-q8_0", + "27b-it-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "llama3.1": { + "tags": [ + "latest", + "8b", + "70b", + "405b", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-q4_0", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16", + "8b-text-q2_K", + "8b-text-q3_K_S", + "8b-text-q3_K_M", + "8b-text-q3_K_L", + "8b-text-q4_0", + "8b-text-q4_1", + "8b-text-q4_K_S", + "8b-text-q4_K_M", + "8b-text-q5_0", + "8b-text-q5_1", + "8b-text-q5_K_S", + "8b-text-q5_K_M", + "8b-text-q6_K", + "8b-text-q8_0", + "8b-text-fp16", + "70b-instruct-q2_K", + "70b-instruct-q3_K_S", + "70b-instruct-q3_K_M", + "70b-instruct-q3_K_L", + "70b-instruct-q4_0", + "70b-instruct-q4_K_S", + "70b-instruct-q4_K_M", + "70b-instruct-q5_0", + "70b-instruct-q5_1", + "70b-instruct-q5_K_S", + "70b-instruct-q5_K_M", + "70b-instruct-q6_K", + "70b-instruct-q8_0", + "70b-instruct-fp16", + "70b-text-q2_K", + "70b-text-q3_K_S", + "70b-text-q3_K_M", + "70b-text-q3_K_L", + "70b-text-q4_0", + "70b-text-q4_1", + "70b-text-q4_K_S", + "70b-text-q4_K_M", + "70b-text-q5_0", + "70b-text-q5_1", + "70b-text-q5_K_S", + "70b-text-q5_K_M", + "70b-text-q6_K", + "70b-text-q8_0", + "70b-text-fp16", + "405b-instruct-q2_K", + "405b-instruct-q3_K_S", + "405b-instruct-q3_K_M", + "405b-instruct-q3_K_L", + "405b-instruct-q4_0", + "405b-instruct-q4_1", + "405b-instruct-q4_K_S", + "405b-instruct-q4_K_M", + "405b-instruct-q5_0", + "405b-instruct-q5_1", + "405b-instruct-q5_K_S", + "405b-instruct-q5_K_M", + "405b-instruct-q6_K", + "405b-instruct-q8_0", + "405b-instruct-fp16", + "405b-text-q2_K", + "405b-text-q3_K_S", + "405b-text-q3_K_M", + "405b-text-q3_K_L", + "405b-text-q4_0", + "405b-text-q4_1", + "405b-text-q4_K_S", + "405b-text-q4_K_M", + "405b-text-q5_0", + "405b-text-q5_1", + "405b-text-q5_K_S", + "405b-text-q5_K_M", + "405b-text-q6_K", + "405b-text-q8_0", + "405b-text-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "llama3.2": { + "tags": [ + "latest", + "1b", + "3b", + "1b-instruct-q2_K", + "1b-instruct-q3_K_S", + "1b-instruct-q3_K_M", + "1b-instruct-q3_K_L", + "1b-instruct-q4_0", + "1b-instruct-q4_1", + "1b-instruct-q4_K_S", + "1b-instruct-q4_K_M", + "1b-instruct-q5_0", + "1b-instruct-q5_1", + "1b-instruct-q5_K_S", + "1b-instruct-q5_K_M", + "1b-instruct-q6_K", + "1b-instruct-q8_0", + "1b-instruct-fp16", + "1b-text-q2_K", + "1b-text-q3_K_S", + "1b-text-q3_K_M", + "1b-text-q3_K_L", + "1b-text-q4_0", + "1b-text-q4_1", + "1b-text-q4_K_S", + "1b-text-q4_K_M", + "1b-text-q5_0", + "1b-text-q5_1", + "1b-text-q5_K_S", + "1b-text-q5_K_M", + "1b-text-q6_K", + "1b-text-q8_0", + "1b-text-fp16", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16", + "3b-text-q2_K", + "3b-text-q3_K_S", + "3b-text-q3_K_M", + "3b-text-q3_K_L", + "3b-text-q4_0", + "3b-text-q4_1", + "3b-text-q4_K_S", + "3b-text-q4_K_M", + "3b-text-q5_0", + "3b-text-q5_1", + "3b-text-q5_K_S", + "3b-text-q5_K_M", + "3b-text-q6_K", + "3b-text-q8_0", + "3b-text-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "nomic-embed-text": { + "tags": [ + "latest", + "v1.5", + "137m-v1.5-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "mistral": { + "tags": [ + "latest", + "instruct", + "text", + "v0.1", + "v0.2", + "v0.3", + "7b", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-v0.2-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-v0.2-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-v0.2-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-v0.2-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-v0.2-q4_0", + "7b-instruct-q4_1", + "7b-instruct-v0.2-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-v0.2-q4_K_S", + "7b-instruct-v0.2-q4_K_M", + "7b-instruct-v0.2-q5_0", + "7b-instruct-v0.2-q5_1", + "7b-instruct-v0.2-q5_K_S", + "7b-instruct-v0.2-q5_K_M", + "7b-instruct-v0.2-q6_K", + "7b-instruct-v0.2-q8_0", + "7b-instruct-v0.2-fp16", + "7b-instruct-v0.3-q2_K", + "7b-instruct-v0.3-q3_K_S", + "7b-instruct-v0.3-q3_K_M", + "7b-instruct-v0.3-q3_K_L", + "7b-instruct-v0.3-q4_0", + "7b-instruct-v0.3-q4_1", + "7b-instruct-v0.3-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-v0.3-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-v0.3-q5_0", + "7b-instruct-q5_1", + "7b-instruct-v0.3-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-v0.3-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-v0.3-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-v0.3-q6_K", + "7b-instruct-q8_0", + "7b-instruct-v0.3-q8_0", + "7b-instruct-fp16", + "7b-instruct-v0.3-fp16", + "7b-text", + "7b-text-q2_K", + "7b-text-v0.2-q2_K", + "7b-text-q3_K_S", + "7b-text-v0.2-q3_K_S", + "7b-text-q3_K_M", + "7b-text-v0.2-q3_K_M", + "7b-text-q3_K_L", + "7b-text-v0.2-q3_K_L", + "7b-text-q4_0", + "7b-text-v0.2-q4_0", + "7b-text-q4_1", + "7b-text-v0.2-q4_1", + "7b-text-q4_K_S", + "7b-text-v0.2-q4_K_S", + "7b-text-q4_K_M", + "7b-text-v0.2-q4_K_M", + "7b-text-q5_0", + "7b-text-v0.2-q5_0", + "7b-text-q5_1", + "7b-text-v0.2-q5_1", + "7b-text-q5_K_S", + "7b-text-v0.2-q5_K_S", + "7b-text-q5_K_M", + "7b-text-v0.2-q5_K_M", + "7b-text-q6_K", + "7b-text-v0.2-q6_K", + "7b-text-q8_0", + "7b-text-v0.2-q8_0", + "7b-text-fp16", + "7b-text-v0.2-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "qwen2.5": { + "tags": [ + "latest", + "0.5b", + "1.5b", + "3b", + "7b", + "14b", + "32b", + "72b", + "0.5b-base", + "0.5b-base-q2_K", + "0.5b-base-q3_K_S", + "0.5b-base-q3_K_M", + "0.5b-base-q3_K_L", + "0.5b-base-q4_0", + "0.5b-base-q4_1", + "0.5b-base-q4_K_S", + "0.5b-base-q4_K_M", + "0.5b-base-q5_0", + "0.5b-base-q5_1", + "0.5b-base-q5_K_S", + "0.5b-base-q8_0", + "0.5b-instruct", + "0.5b-instruct-q2_K", + "0.5b-instruct-q3_K_S", + "0.5b-instruct-q3_K_M", + "0.5b-instruct-q3_K_L", + "0.5b-instruct-q4_0", + "0.5b-instruct-q4_1", + "0.5b-instruct-q4_K_S", + "0.5b-instruct-q4_K_M", + "0.5b-instruct-q5_0", + "0.5b-instruct-q5_1", + "0.5b-instruct-q5_K_S", + "0.5b-instruct-q5_K_M", + "0.5b-instruct-q6_K", + "0.5b-instruct-q8_0", + "0.5b-instruct-fp16", + "1.5b-instruct", + "1.5b-instruct-q2_K", + "1.5b-instruct-q3_K_S", + "1.5b-instruct-q3_K_M", + "1.5b-instruct-q3_K_L", + "1.5b-instruct-q4_0", + "1.5b-instruct-q4_1", + "1.5b-instruct-q4_K_S", + "1.5b-instruct-q4_K_M", + "1.5b-instruct-q5_0", + "1.5b-instruct-q5_1", + "1.5b-instruct-q5_K_S", + "1.5b-instruct-q5_K_M", + "1.5b-instruct-q6_K", + "1.5b-instruct-q8_0", + "1.5b-instruct-fp16", + "3b-instruct", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "14b-instruct", + "14b-instruct-q2_K", + "14b-instruct-q3_K_S", + "14b-instruct-q3_K_M", + "14b-instruct-q3_K_L", + "14b-instruct-q4_0", + "14b-instruct-q4_1", + "14b-instruct-q4_K_S", + "14b-instruct-q4_K_M", + "14b-instruct-q5_0", + "14b-instruct-q5_1", + "14b-instruct-q5_K_S", + "14b-instruct-q5_K_M", + "14b-instruct-q6_K", + "14b-instruct-q8_0", + "14b-instruct-fp16", + "32b-instruct", + "32b-instruct-q2_K", + "32b-instruct-q3_K_S", + "32b-instruct-q3_K_M", + "32b-instruct-q3_K_L", + "32b-instruct-q4_0", + "32b-instruct-q4_1", + "32b-instruct-q4_K_S", + "32b-instruct-q4_K_M", + "32b-instruct-q5_0", + "32b-instruct-q5_1", + "32b-instruct-q5_K_S", + "32b-instruct-q5_K_M", + "32b-instruct-q6_K", + "32b-instruct-q8_0", + "32b-instruct-fp16", + "72b-instruct", + "72b-instruct-q2_K", + "72b-instruct-q3_K_S", + "72b-instruct-q3_K_M", + "72b-instruct-q3_K_L", + "72b-instruct-q4_0", + "72b-instruct-q4_1", + "72b-instruct-q4_K_S", + "72b-instruct-q4_K_M", + "72b-instruct-q5_0", + "72b-instruct-q5_1", + "72b-instruct-q5_K_S", + "72b-instruct-q5_K_M", + "72b-instruct-q6_K", + "72b-instruct-q8_0", + "72b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "qwen3": { + "tags": [ + "latest", + "0.6b", + "1.7b", + "4b", + "8b", + "14b", + "30b", + "32b", + "235b", + "0.6b-q4_K_M", + "0.6b-q8_0", + "0.6b-fp16", + "1.7b-q4_K_M", + "1.7b-q8_0", + "1.7b-fp16", + "4b-instruct", + "4b-instruct-2507-q4_K_M", + "4b-instruct-2507-q8_0", + "4b-instruct-2507-fp16", + "4b-thinking", + "4b-thinking-2507-q4_K_M", + "4b-thinking-2507-q8_0", + "4b-thinking-2507-fp16", + "4b-q4_K_M", + "4b-q8_0", + "4b-fp16", + "8b-q4_K_M", + "8b-q8_0", + "8b-fp16", + "14b-q4_K_M", + "14b-q8_0", + "14b-fp16", + "30b-a3b", + "30b-a3b-instruct-2507-q4_K_M", + "30b-a3b-q4_K_M", + "30b-a3b-instruct-2507-q8_0", + "30b-a3b-thinking-2507-q4_K_M", + "30b-a3b-q8_0", + "30b-a3b-thinking-2507-q8_0", + "30b-a3b-fp16", + "30b-a3b-instruct-2507-fp16", + "30b-a3b-thinking-2507-fp16", + "30b-instruct", + "30b-thinking", + "32b-q4_K_M", + "32b-q8_0", + "32b-fp16", + "235b-a22b", + "235b-a22b-instruct-2507-q4_K_M", + "235b-a22b-q4_K_M", + "235b-a22b-instruct-2507-q8_0", + "235b-a22b-thinking-2507-q4_K_M", + "235b-a22b-q8_0", + "235b-a22b-thinking-2507-q8_0", + "235b-a22b-fp16", + "235b-a22b-thinking-2507-fp16", + "235b-instruct", + "235b-thinking" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "phi3": { + "tags": [ + "latest", + "instruct", + "medium", + "mini", + "3.8b", + "14b", + "3.8b-instruct", + "3.8b-mini-128k-instruct-q2_K", + "3.8b-mini-128k-instruct-q3_K_S", + "3.8b-mini-128k-instruct-q3_K_M", + "3.8b-mini-128k-instruct-q3_K_L", + "3.8b-mini-128k-instruct-q4_0", + "3.8b-mini-128k-instruct-q4_1", + "3.8b-mini-128k-instruct-q4_K_S", + "3.8b-mini-128k-instruct-q4_K_M", + "3.8b-mini-128k-instruct-q5_0", + "3.8b-mini-128k-instruct-q5_1", + "3.8b-mini-128k-instruct-q5_K_S", + "3.8b-mini-128k-instruct-q5_K_M", + "3.8b-mini-128k-instruct-q6_K", + "3.8b-mini-128k-instruct-q8_0", + "3.8b-mini-128k-instruct-fp16", + "3.8b-mini-4k-instruct-q2_K", + "3.8b-mini-4k-instruct-q3_K_S", + "3.8b-mini-4k-instruct-q3_K_M", + "3.8b-mini-4k-instruct-q3_K_L", + "3.8b-mini-4k-instruct-q4_0", + "3.8b-mini-4k-instruct-q4_1", + "3.8b-mini-4k-instruct-q4_K_S", + "3.8b-mini-4k-instruct-q4_K_M", + "3.8b-mini-4k-instruct-q5_0", + "3.8b-mini-4k-instruct-q5_1", + "3.8b-mini-4k-instruct-q5_K_S", + "3.8b-mini-4k-instruct-q5_K_M", + "3.8b-mini-4k-instruct-q6_K", + "3.8b-mini-4k-instruct-q8_0", + "3.8b-mini-4k-instruct-fp16", + "14b-instruct", + "14b-medium-128k-instruct-q2_K", + "14b-medium-128k-instruct-q3_K_S", + "14b-medium-128k-instruct-q3_K_M", + "14b-medium-128k-instruct-q3_K_L", + "14b-medium-128k-instruct-q4_0", + "14b-medium-128k-instruct-q4_1", + "14b-medium-128k-instruct-q4_K_S", + "14b-medium-128k-instruct-q4_K_M", + "14b-medium-128k-instruct-q5_0", + "14b-medium-128k-instruct-q5_1", + "14b-medium-128k-instruct-q5_K_S", + "14b-medium-128k-instruct-q5_K_M", + "14b-medium-128k-instruct-q6_K", + "14b-medium-128k-instruct-q8_0", + "14b-medium-128k-instruct-fp16", + "14b-medium-4k-instruct-q2_K", + "14b-medium-4k-instruct-q3_K_S", + "14b-medium-4k-instruct-q3_K_M", + "14b-medium-4k-instruct-q3_K_L", + "14b-medium-4k-instruct-q4_0", + "14b-medium-4k-instruct-q4_1", + "14b-medium-4k-instruct-q4_K_S", + "14b-medium-4k-instruct-q4_K_M", + "14b-medium-4k-instruct-q5_0", + "14b-medium-4k-instruct-q5_1", + "14b-medium-4k-instruct-q5_K_S", + "14b-medium-4k-instruct-q5_K_M", + "14b-medium-4k-instruct-q6_K", + "14b-medium-4k-instruct-q8_0", + "14b-medium-4k-instruct-fp16", + "medium-128k", + "medium-4k", + "mini-128k", + "mini-4k" + ], + "capabilities": [] + }, + "llama3": { + "tags": [ + "latest", + "instruct", + "text", + "8b", + "70b", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-q4_0", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16", + "8b-text", + "8b-text-q2_K", + "8b-text-q3_K_S", + "8b-text-q3_K_M", + "8b-text-q3_K_L", + "8b-text-q4_0", + "8b-text-q4_1", + "8b-text-q4_K_S", + "8b-text-q4_K_M", + "8b-text-q5_0", + "8b-text-q5_1", + "8b-text-q5_K_S", + "8b-text-q5_K_M", + "8b-text-q6_K", + "8b-text-q8_0", + "8b-text-fp16", + "70b-instruct", + "70b-instruct-q2_K", + "70b-instruct-q3_K_S", + "70b-instruct-q3_K_M", + "70b-instruct-q3_K_L", + "70b-instruct-q4_0", + "70b-instruct-q4_1", + "70b-instruct-q4_K_S", + "70b-instruct-q4_K_M", + "70b-instruct-q5_0", + "70b-instruct-q5_1", + "70b-instruct-q5_K_S", + "70b-instruct-q5_K_M", + "70b-instruct-q6_K", + "70b-instruct-q8_0", + "70b-instruct-fp16", + "70b-text", + "70b-text-q2_K", + "70b-text-q3_K_S", + "70b-text-q3_K_M", + "70b-text-q3_K_L", + "70b-text-q4_0", + "70b-text-q4_1", + "70b-text-q4_K_S", + "70b-text-q4_K_M", + "70b-text-q5_0", + "70b-text-q5_1", + "70b-text-q5_K_S", + "70b-text-q5_K_M", + "70b-text-q6_K", + "70b-text-q8_0", + "70b-text-fp16" + ], + "capabilities": [] + }, + "gemma2": { + "tags": [ + "latest", + "2b", + "9b", + "27b", + "2b-instruct-q2_K", + "2b-instruct-q3_K_S", + "2b-instruct-q3_K_M", + "2b-instruct-q3_K_L", + "2b-instruct-q4_0", + "2b-instruct-q4_1", + "2b-instruct-q4_K_S", + "2b-instruct-q4_K_M", + "2b-instruct-q5_0", + "2b-instruct-q5_1", + "2b-instruct-q5_K_S", + "2b-instruct-q5_K_M", + "2b-instruct-q6_K", + "2b-instruct-q8_0", + "2b-instruct-fp16", + "2b-text-q2_K", + "2b-text-q3_K_S", + "2b-text-q3_K_M", + "2b-text-q3_K_L", + "2b-text-q4_0", + "2b-text-q4_1", + "2b-text-q4_K_S", + "2b-text-q4_K_M", + "2b-text-q5_0", + "2b-text-q5_1", + "2b-text-q5_K_S", + "2b-text-q5_K_M", + "2b-text-q6_K", + "2b-text-q8_0", + "2b-text-fp16", + "9b-instruct-q2_K", + "9b-instruct-q3_K_S", + "9b-instruct-q3_K_M", + "9b-instruct-q3_K_L", + "9b-instruct-q4_0", + "9b-instruct-q4_1", + "9b-instruct-q4_K_S", + "9b-instruct-q4_K_M", + "9b-instruct-q5_0", + "9b-instruct-q5_1", + "9b-instruct-q5_K_S", + "9b-instruct-q5_K_M", + "9b-instruct-q6_K", + "9b-instruct-q8_0", + "9b-instruct-fp16", + "9b-text-q2_K", + "9b-text-q3_K_S", + "9b-text-q3_K_M", + "9b-text-q3_K_L", + "9b-text-q4_0", + "9b-text-q4_1", + "9b-text-q4_K_S", + "9b-text-q4_K_M", + "9b-text-q5_0", + "9b-text-q5_1", + "9b-text-q5_K_S", + "9b-text-q5_K_M", + "9b-text-q6_K", + "9b-text-q8_0", + "9b-text-fp16", + "27b-instruct-q2_K", + "27b-instruct-q3_K_S", + "27b-instruct-q3_K_M", + "27b-instruct-q3_K_L", + "27b-instruct-q4_0", + "27b-instruct-q4_1", + "27b-instruct-q4_K_S", + "27b-instruct-q4_K_M", + "27b-instruct-q5_0", + "27b-instruct-q5_1", + "27b-instruct-q5_K_S", + "27b-instruct-q5_K_M", + "27b-instruct-q6_K", + "27b-instruct-q8_0", + "27b-instruct-fp16", + "27b-text-q2_K", + "27b-text-q3_K_S", + "27b-text-q3_K_M", + "27b-text-q3_K_L", + "27b-text-q4_0", + "27b-text-q4_1", + "27b-text-q4_K_S", + "27b-text-q4_K_M", + "27b-text-q5_0", + "27b-text-q5_1", + "27b-text-q5_K_S", + "27b-text-q5_K_M", + "27b-text-q6_K", + "27b-text-q8_0", + "27b-text-fp16" + ], + "capabilities": [] + }, + "llava": { + "tags": [ + "latest", + "v1.6", + "7b", + "13b", + "34b", + "7b-v1.5-q2_K", + "7b-v1.5-q3_K_S", + "7b-v1.5-q3_K_M", + "7b-v1.5-q3_K_L", + "7b-v1.5-q4_0", + "7b-v1.5-q4_1", + "7b-v1.5-q4_K_S", + "7b-v1.5-q4_K_M", + "7b-v1.5-q5_0", + "7b-v1.5-q5_1", + "7b-v1.5-q5_K_S", + "7b-v1.5-q5_K_M", + "7b-v1.5-q6_K", + "7b-v1.5-q8_0", + "7b-v1.5-fp16", + "7b-v1.6", + "7b-v1.6-mistral-q2_K", + "7b-v1.6-mistral-q3_K_S", + "7b-v1.6-mistral-q3_K_M", + "7b-v1.6-mistral-q3_K_L", + "7b-v1.6-mistral-q4_0", + "7b-v1.6-mistral-q4_1", + "7b-v1.6-mistral-q4_K_S", + "7b-v1.6-mistral-q4_K_M", + "7b-v1.6-mistral-q5_0", + "7b-v1.6-mistral-q5_1", + "7b-v1.6-mistral-q5_K_S", + "7b-v1.6-mistral-q5_K_M", + "7b-v1.6-mistral-q6_K", + "7b-v1.6-mistral-q8_0", + "7b-v1.6-mistral-fp16", + "7b-v1.6-vicuna-q2_K", + "7b-v1.6-vicuna-q3_K_S", + "7b-v1.6-vicuna-q3_K_M", + "7b-v1.6-vicuna-q3_K_L", + "7b-v1.6-vicuna-q4_0", + "7b-v1.6-vicuna-q4_1", + "7b-v1.6-vicuna-q4_K_S", + "7b-v1.6-vicuna-q4_K_M", + "7b-v1.6-vicuna-q5_0", + "7b-v1.6-vicuna-q5_1", + "7b-v1.6-vicuna-q5_K_S", + "7b-v1.6-vicuna-q5_K_M", + "7b-v1.6-vicuna-q6_K", + "7b-v1.6-vicuna-q8_0", + "7b-v1.6-vicuna-fp16", + "13b-v1.5-q2_K", + "13b-v1.5-q3_K_S", + "13b-v1.5-q3_K_M", + "13b-v1.5-q3_K_L", + "13b-v1.5-q4_0", + "13b-v1.5-q4_1", + "13b-v1.5-q4_K_S", + "13b-v1.5-q4_K_M", + "13b-v1.5-q5_0", + "13b-v1.5-q5_1", + "13b-v1.5-q5_K_S", + "13b-v1.5-q5_K_M", + "13b-v1.5-q6_K", + "13b-v1.5-q8_0", + "13b-v1.5-fp16", + "13b-v1.6", + "13b-v1.6-vicuna-q2_K", + "13b-v1.6-vicuna-q3_K_S", + "13b-v1.6-vicuna-q3_K_M", + "13b-v1.6-vicuna-q3_K_L", + "13b-v1.6-vicuna-q4_0", + "13b-v1.6-vicuna-q4_1", + "13b-v1.6-vicuna-q4_K_S", + "13b-v1.6-vicuna-q4_K_M", + "13b-v1.6-vicuna-q5_0", + "13b-v1.6-vicuna-q5_1", + "13b-v1.6-vicuna-q5_K_S", + "13b-v1.6-vicuna-q5_K_M", + "13b-v1.6-vicuna-q6_K", + "13b-v1.6-vicuna-q8_0", + "13b-v1.6-vicuna-fp16", + "34b-v1.6", + "34b-v1.6-q2_K", + "34b-v1.6-q3_K_S", + "34b-v1.6-q3_K_M", + "34b-v1.6-q3_K_L", + "34b-v1.6-q4_0", + "34b-v1.6-q4_1", + "34b-v1.6-q4_K_S", + "34b-v1.6-q4_K_M", + "34b-v1.6-q5_0", + "34b-v1.6-q5_1", + "34b-v1.6-q5_K_S", + "34b-v1.6-q5_K_M", + "34b-v1.6-q6_K", + "34b-v1.6-q8_0", + "34b-v1.6-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "qwen2.5-coder": { + "tags": [ + "latest", + "0.5b", + "1.5b", + "3b", + "7b", + "14b", + "32b", + "0.5b-base", + "0.5b-base-q2_K", + "0.5b-base-q3_K_S", + "0.5b-base-q3_K_M", + "0.5b-base-q3_K_L", + "0.5b-base-q4_0", + "0.5b-base-q4_1", + "0.5b-base-q4_K_S", + "0.5b-base-q4_K_M", + "0.5b-base-q5_0", + "0.5b-base-q5_1", + "0.5b-base-q5_K_S", + "0.5b-base-q5_K_M", + "0.5b-base-q6_K", + "0.5b-base-q8_0", + "0.5b-base-fp16", + "0.5b-instruct", + "0.5b-instruct-q2_K", + "0.5b-instruct-q3_K_S", + "0.5b-instruct-q3_K_M", + "0.5b-instruct-q3_K_L", + "0.5b-instruct-q4_0", + "0.5b-instruct-q4_1", + "0.5b-instruct-q4_K_S", + "0.5b-instruct-q4_K_M", + "0.5b-instruct-q5_0", + "0.5b-instruct-q5_1", + "0.5b-instruct-q5_K_S", + "0.5b-instruct-q5_K_M", + "0.5b-instruct-q6_K", + "0.5b-instruct-q8_0", + "0.5b-instruct-fp16", + "1.5b-base", + "1.5b-base-q2_K", + "1.5b-base-q3_K_S", + "1.5b-base-q3_K_M", + "1.5b-base-q3_K_L", + "1.5b-base-q4_0", + "1.5b-base-q4_1", + "1.5b-base-q4_K_S", + "1.5b-base-q4_K_M", + "1.5b-base-q5_0", + "1.5b-base-q5_1", + "1.5b-base-q5_K_S", + "1.5b-base-q5_K_M", + "1.5b-base-q6_K", + "1.5b-base-q8_0", + "1.5b-base-fp16", + "1.5b-instruct", + "1.5b-instruct-q2_K", + "1.5b-instruct-q3_K_S", + "1.5b-instruct-q3_K_M", + "1.5b-instruct-q3_K_L", + "1.5b-instruct-q4_0", + "1.5b-instruct-q4_1", + "1.5b-instruct-q4_K_S", + "1.5b-instruct-q4_K_M", + "1.5b-instruct-q5_0", + "1.5b-instruct-q5_1", + "1.5b-instruct-q5_K_S", + "1.5b-instruct-q5_K_M", + "1.5b-instruct-q6_K", + "1.5b-instruct-q8_0", + "1.5b-instruct-fp16", + "3b-base", + "3b-base-q2_K", + "3b-base-q3_K_S", + "3b-base-q3_K_M", + "3b-base-q3_K_L", + "3b-base-q4_0", + "3b-base-q4_1", + "3b-base-q4_K_S", + "3b-base-q4_K_M", + "3b-base-q5_0", + "3b-base-q5_1", + "3b-base-q5_K_S", + "3b-base-q5_K_M", + "3b-base-q6_K", + "3b-base-q8_0", + "3b-base-fp16", + "3b-instruct", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16", + "7b-base", + "7b-base-q2_K", + "7b-base-q3_K_S", + "7b-base-q3_K_M", + "7b-base-q3_K_L", + "7b-base-q4_0", + "7b-base-q4_1", + "7b-base-q4_K_S", + "7b-base-q4_K_M", + "7b-base-q5_0", + "7b-base-q5_1", + "7b-base-q5_K_S", + "7b-base-q5_K_M", + "7b-base-q6_K", + "7b-base-q8_0", + "7b-base-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "14b-base", + "14b-base-q2_K", + "14b-base-q3_K_S", + "14b-base-q3_K_M", + "14b-base-q3_K_L", + "14b-base-q4_0", + "14b-base-q4_1", + "14b-base-q4_K_S", + "14b-base-q4_K_M", + "14b-base-q5_0", + "14b-base-q5_1", + "14b-base-q5_K_S", + "14b-base-q5_K_M", + "14b-base-q6_K", + "14b-base-q8_0", + "14b-base-fp16", + "14b-instruct", + "14b-instruct-q2_K", + "14b-instruct-q3_K_S", + "14b-instruct-q3_K_M", + "14b-instruct-q3_K_L", + "14b-instruct-q4_0", + "14b-instruct-q4_1", + "14b-instruct-q4_K_S", + "14b-instruct-q4_K_M", + "14b-instruct-q5_0", + "14b-instruct-q5_1", + "14b-instruct-q5_K_S", + "14b-instruct-q5_K_M", + "14b-instruct-q6_K", + "14b-instruct-q8_0", + "14b-instruct-fp16", + "32b-base", + "32b-base-q2_K", + "32b-base-q3_K_S", + "32b-base-q3_K_M", + "32b-base-q3_K_L", + "32b-base-q4_0", + "32b-base-q4_1", + "32b-base-q4_K_S", + "32b-base-q4_K_M", + "32b-base-q5_0", + "32b-base-q5_1", + "32b-base-q5_K_S", + "32b-base-q5_K_M", + "32b-base-q6_K", + "32b-base-q8_0", + "32b-base-fp16", + "32b-instruct", + "32b-instruct-q2_K", + "32b-instruct-q3_K_S", + "32b-instruct-q3_K_M", + "32b-instruct-q3_K_L", + "32b-instruct-q4_0", + "32b-instruct-q4_1", + "32b-instruct-q4_K_S", + "32b-instruct-q4_K_M", + "32b-instruct-q5_0", + "32b-instruct-q5_1", + "32b-instruct-q5_K_S", + "32b-instruct-q5_K_M", + "32b-instruct-q6_K", + "32b-instruct-q8_0", + "32b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "phi4": { + "tags": [ + "latest", + "14b", + "14b-q4_K_M", + "14b-q8_0", + "14b-fp16" + ], + "capabilities": [] + }, + "mxbai-embed-large": { + "tags": [ + "latest", + "v1", + "335m", + "335m-v1-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "gemma": { + "tags": [ + "latest", + "instruct", + "text", + "v1.1", + "2b", + "7b", + "2b-instruct", + "2b-instruct-q2_K", + "2b-instruct-v1.1-q2_K", + "2b-instruct-q3_K_S", + "2b-instruct-v1.1-q3_K_S", + "2b-instruct-q3_K_M", + "2b-instruct-v1.1-q3_K_M", + "2b-instruct-q3_K_L", + "2b-instruct-v1.1-q3_K_L", + "2b-instruct-q4_0", + "2b-instruct-v1.1-q4_0", + "2b-instruct-q4_1", + "2b-instruct-v1.1-q4_1", + "2b-instruct-q4_K_S", + "2b-instruct-v1.1-q4_K_S", + "2b-instruct-q4_K_M", + "2b-instruct-v1.1-q4_K_M", + "2b-instruct-q5_0", + "2b-instruct-v1.1-q5_0", + "2b-instruct-q5_1", + "2b-instruct-v1.1-q5_1", + "2b-instruct-q5_K_S", + "2b-instruct-v1.1-q5_K_S", + "2b-instruct-q5_K_M", + "2b-instruct-v1.1-q5_K_M", + "2b-instruct-q6_K", + "2b-instruct-v1.1-q6_K", + "2b-instruct-q8_0", + "2b-instruct-v1.1-q8_0", + "2b-instruct-fp16", + "2b-instruct-v1.1-fp16", + "2b-text", + "2b-text-q2_K", + "2b-text-q3_K_S", + "2b-text-q3_K_M", + "2b-text-q3_K_L", + "2b-text-q4_0", + "2b-text-q4_1", + "2b-text-q4_K_S", + "2b-text-q4_K_M", + "2b-text-q5_0", + "2b-text-q5_1", + "2b-text-q5_K_S", + "2b-text-q5_K_M", + "2b-text-q6_K", + "2b-text-q8_0", + "2b-text-fp16", + "2b-v1.1", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-v1.1-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-v1.1-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-v1.1-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-v1.1-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-v1.1-q4_0", + "7b-instruct-q4_1", + "7b-instruct-v1.1-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-v1.1-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-v1.1-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-v1.1-q5_0", + "7b-instruct-q5_1", + "7b-instruct-v1.1-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-v1.1-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-v1.1-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-v1.1-q6_K", + "7b-instruct-q8_0", + "7b-instruct-v1.1-q8_0", + "7b-instruct-fp16", + "7b-instruct-v1.1-fp16", + "7b-text", + "7b-text-q2_K", + "7b-text-q3_K_S", + "7b-text-q3_K_M", + "7b-text-q3_K_L", + "7b-text-q4_0", + "7b-text-q4_1", + "7b-text-q4_K_S", + "7b-text-q4_K_M", + "7b-text-q5_0", + "7b-text-q5_1", + "7b-text-q5_K_S", + "7b-text-q5_K_M", + "7b-text-q6_K", + "7b-text-q8_0", + "7b-text-fp16", + "7b-v1.1" + ], + "capabilities": [] + }, + "qwen": { + "tags": [ + "latest", + "0.5b", + "1.8b", + "4b", + "7b", + "14b", + "32b", + "72b", + "110b", + "0.5b-chat", + "0.5b-chat-v1.5-q2_K", + "0.5b-chat-v1.5-q3_K_S", + "0.5b-chat-v1.5-q3_K_M", + "0.5b-chat-v1.5-q3_K_L", + "0.5b-chat-v1.5-q4_0", + "0.5b-chat-v1.5-q4_1", + "0.5b-chat-v1.5-q4_K_S", + "0.5b-chat-v1.5-q4_K_M", + "0.5b-chat-v1.5-q5_0", + "0.5b-chat-v1.5-q5_1", + "0.5b-chat-v1.5-q5_K_S", + "0.5b-chat-v1.5-q5_K_M", + "0.5b-chat-v1.5-q6_K", + "0.5b-chat-v1.5-q8_0", + "0.5b-chat-v1.5-fp16", + "0.5b-text", + "0.5b-text-v1.5-q2_K", + "0.5b-text-v1.5-q3_K_S", + "0.5b-text-v1.5-q3_K_M", + "0.5b-text-v1.5-q3_K_L", + "0.5b-text-v1.5-q4_0", + "0.5b-text-v1.5-q4_1", + "0.5b-text-v1.5-q4_K_S", + "0.5b-text-v1.5-q4_K_M", + "0.5b-text-v1.5-q5_0", + "0.5b-text-v1.5-q5_1", + "0.5b-text-v1.5-q5_K_S", + "0.5b-text-v1.5-q5_K_M", + "0.5b-text-v1.5-q6_K", + "0.5b-text-v1.5-q8_0", + "0.5b-text-v1.5-fp16", + "1.8b-chat", + "1.8b-chat-q2_K", + "1.8b-chat-v1.5-q2_K", + "1.8b-chat-q3_K_S", + "1.8b-chat-v1.5-q3_K_S", + "1.8b-chat-q3_K_M", + "1.8b-chat-v1.5-q3_K_M", + "1.8b-chat-q3_K_L", + "1.8b-chat-v1.5-q3_K_L", + "1.8b-chat-q4_0", + "1.8b-chat-v1.5-q4_0", + "1.8b-chat-q4_1", + "1.8b-chat-v1.5-q4_1", + "1.8b-chat-q4_K_S", + "1.8b-chat-v1.5-q4_K_S", + "1.8b-chat-q4_K_M", + "1.8b-chat-v1.5-q4_K_M", + "1.8b-chat-q5_0", + "1.8b-chat-v1.5-q5_0", + "1.8b-chat-q5_1", + "1.8b-chat-v1.5-q5_1", + "1.8b-chat-q5_K_S", + "1.8b-chat-v1.5-q5_K_S", + "1.8b-chat-q5_K_M", + "1.8b-chat-v1.5-q5_K_M", + "1.8b-chat-q6_K", + "1.8b-chat-v1.5-q6_K", + "1.8b-chat-q8_0", + "1.8b-chat-v1.5-q8_0", + "1.8b-chat-fp16", + "1.8b-chat-v1.5-fp16", + "1.8b-text", + "1.8b-text-q2_K", + "1.8b-text-v1.5-q2_K", + "1.8b-text-q3_K_S", + "1.8b-text-v1.5-q3_K_S", + "1.8b-text-q3_K_M", + "1.8b-text-v1.5-q3_K_M", + "1.8b-text-q3_K_L", + "1.8b-text-v1.5-q3_K_L", + "1.8b-text-q4_0", + "1.8b-text-v1.5-q4_0", + "1.8b-text-q4_1", + "1.8b-text-v1.5-q4_1", + "1.8b-text-q4_K_S", + "1.8b-text-v1.5-q4_K_S", + "1.8b-text-q4_K_M", + "1.8b-text-v1.5-q4_K_M", + "1.8b-text-q5_0", + "1.8b-text-v1.5-q5_0", + "1.8b-text-q5_1", + "1.8b-text-v1.5-q5_1", + "1.8b-text-q5_K_S", + "1.8b-text-v1.5-q5_K_S", + "1.8b-text-q5_K_M", + "1.8b-text-v1.5-q5_K_M", + "1.8b-text-q6_K", + "1.8b-text-v1.5-q6_K", + "1.8b-text-q8_0", + "1.8b-text-v1.5-q8_0", + "1.8b-text-fp16", + "1.8b-text-v1.5-fp16", + "4b-chat", + "4b-chat-v1.5-q2_K", + "4b-chat-v1.5-q3_K_S", + "4b-chat-v1.5-q3_K_M", + "4b-chat-v1.5-q3_K_L", + "4b-chat-v1.5-q4_0", + "4b-chat-v1.5-q4_1", + "4b-chat-v1.5-q4_K_S", + "4b-chat-v1.5-q4_K_M", + "4b-chat-v1.5-q5_0", + "4b-chat-v1.5-q5_1", + "4b-chat-v1.5-q5_K_S", + "4b-chat-v1.5-q5_K_M", + "4b-chat-v1.5-q6_K", + "4b-chat-v1.5-q8_0", + "4b-chat-v1.5-fp16", + "4b-text", + "4b-text-v1.5-q2_K", + "4b-text-v1.5-q3_K_S", + "4b-text-v1.5-q3_K_M", + "4b-text-v1.5-q3_K_L", + "4b-text-v1.5-q4_0", + "4b-text-v1.5-q4_1", + "4b-text-v1.5-q4_K_S", + "4b-text-v1.5-q4_K_M", + "4b-text-v1.5-q5_0", + "4b-text-v1.5-q5_1", + "4b-text-v1.5-q5_K_S", + "4b-text-v1.5-q5_K_M", + "4b-text-v1.5-q6_K", + "4b-text-v1.5-q8_0", + "4b-text-v1.5-fp16", + "7b-chat", + "7b-chat-q2_K", + "7b-chat-v1.5-q2_K", + "7b-chat-q3_K_S", + "7b-chat-v1.5-q3_K_S", + "7b-chat-q3_K_M", + "7b-chat-v1.5-q3_K_M", + "7b-chat-q3_K_L", + "7b-chat-v1.5-q3_K_L", + "7b-chat-q4_0", + "7b-chat-v1.5-q4_0", + "7b-chat-q4_1", + "7b-chat-v1.5-q4_1", + "7b-chat-q4_K_S", + "7b-chat-v1.5-q4_K_S", + "7b-chat-q4_K_M", + "7b-chat-v1.5-q4_K_M", + "7b-chat-q5_0", + "7b-chat-v1.5-q5_0", + "7b-chat-q5_1", + "7b-chat-v1.5-q5_1", + "7b-chat-q5_K_S", + "7b-chat-v1.5-q5_K_S", + "7b-chat-q5_K_M", + "7b-chat-v1.5-q5_K_M", + "7b-chat-q6_K", + "7b-chat-v1.5-q6_K", + "7b-chat-q8_0", + "7b-chat-v1.5-q8_0", + "7b-chat-fp16", + "7b-chat-v1.5-fp16", + "7b-text", + "7b-text-v1.5-q2_K", + "7b-text-v1.5-q3_K_S", + "7b-text-v1.5-q3_K_M", + "7b-text-v1.5-q3_K_L", + "7b-text-v1.5-q4_0", + "7b-text-v1.5-q4_1", + "7b-text-v1.5-q4_K_S", + "7b-text-v1.5-q4_K_M", + "7b-text-v1.5-q5_0", + "7b-text-v1.5-q5_1", + "7b-text-v1.5-q5_K_S", + "7b-text-v1.5-q5_K_M", + "7b-text-v1.5-q6_K", + "7b-text-v1.5-q8_0", + "7b-text-v1.5-fp16", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "14b-chat", + "14b-chat-q2_K", + "14b-chat-v1.5-q2_K", + "14b-chat-q3_K_S", + "14b-chat-v1.5-q3_K_S", + "14b-chat-q3_K_M", + "14b-chat-v1.5-q3_K_M", + "14b-chat-q3_K_L", + "14b-chat-v1.5-q3_K_L", + "14b-chat-q4_0", + "14b-chat-v1.5-q4_0", + "14b-chat-q4_1", + "14b-chat-v1.5-q4_1", + "14b-chat-q4_K_S", + "14b-chat-v1.5-q4_K_S", + "14b-chat-q4_K_M", + "14b-chat-v1.5-q4_K_M", + "14b-chat-q5_0", + "14b-chat-v1.5-q5_0", + "14b-chat-q5_1", + "14b-chat-v1.5-q5_1", + "14b-chat-q5_K_S", + "14b-chat-v1.5-q5_K_S", + "14b-chat-q5_K_M", + "14b-chat-v1.5-q5_K_M", + "14b-chat-q6_K", + "14b-chat-v1.5-q6_K", + "14b-chat-q8_0", + "14b-chat-v1.5-q8_0", + "14b-chat-fp16", + "14b-chat-v1.5-fp16", + "14b-text", + "14b-text-q2_K", + "14b-text-v1.5-q2_K", + "14b-text-q3_K_S", + "14b-text-v1.5-q3_K_S", + "14b-text-q3_K_M", + "14b-text-v1.5-q3_K_M", + "14b-text-q3_K_L", + "14b-text-v1.5-q3_K_L", + "14b-text-q4_0", + "14b-text-v1.5-q4_0", + "14b-text-q4_1", + "14b-text-v1.5-q4_1", + "14b-text-q4_K_S", + "14b-text-v1.5-q4_K_S", + "14b-text-q4_K_M", + "14b-text-v1.5-q4_K_M", + "14b-text-q5_0", + "14b-text-v1.5-q5_0", + "14b-text-q5_1", + "14b-text-v1.5-q5_1", + "14b-text-q5_K_S", + "14b-text-v1.5-q5_K_S", + "14b-text-q5_K_M", + "14b-text-v1.5-q5_K_M", + "14b-text-q6_K", + "14b-text-v1.5-q6_K", + "14b-text-q8_0", + "14b-text-v1.5-q8_0", + "14b-text-fp16", + "14b-text-v1.5-fp16", + "32b-chat", + "32b-chat-v1.5-q2_K", + "32b-chat-v1.5-q3_K_S", + "32b-chat-v1.5-q3_K_M", + "32b-chat-v1.5-q3_K_L", + "32b-chat-v1.5-q4_0", + "32b-chat-v1.5-q4_1", + "32b-chat-v1.5-q4_K_S", + "32b-chat-v1.5-q4_K_M", + "32b-chat-v1.5-q5_0", + "32b-chat-v1.5-q5_1", + "32b-chat-v1.5-q5_K_S", + "32b-chat-v1.5-q5_K_M", + "32b-chat-v1.5-q6_K", + "32b-chat-v1.5-q8_0", + "32b-chat-v1.5-fp16", + "32b-text", + "32b-text-v1.5-q2_K", + "32b-text-v1.5-q3_K_S", + "32b-text-v1.5-q3_K_M", + "32b-text-v1.5-q3_K_L", + "32b-text-v1.5-q4_0", + "32b-text-v1.5-q4_1", + "32b-text-v1.5-q4_K_S", + "32b-text-v1.5-q5_0", + "32b-text-v1.5-q5_1", + "32b-text-v1.5-q8_0", + "72b-chat", + "72b-chat-q2_K", + "72b-chat-v1.5-q2_K", + "72b-chat-q3_K_S", + "72b-chat-v1.5-q3_K_S", + "72b-chat-q3_K_M", + "72b-chat-v1.5-q3_K_M", + "72b-chat-q3_K_L", + "72b-chat-v1.5-q3_K_L", + "72b-chat-q4_0", + "72b-chat-v1.5-q4_0", + "72b-chat-q4_1", + "72b-chat-v1.5-q4_1", + "72b-chat-q4_K_S", + "72b-chat-v1.5-q4_K_S", + "72b-chat-q4_K_M", + "72b-chat-v1.5-q4_K_M", + "72b-chat-q5_0", + "72b-chat-v1.5-q5_0", + "72b-chat-q5_1", + "72b-chat-v1.5-q5_1", + "72b-chat-q5_K_S", + "72b-chat-v1.5-q5_K_S", + "72b-chat-q5_K_M", + "72b-chat-v1.5-q5_K_M", + "72b-chat-q6_K", + "72b-chat-v1.5-q6_K", + "72b-chat-q8_0", + "72b-chat-v1.5-q8_0", + "72b-chat-fp16", + "72b-chat-v1.5-fp16", + "72b-text", + "72b-text-q2_K", + "72b-text-v1.5-q2_K", + "72b-text-q3_K_S", + "72b-text-v1.5-q3_K_S", + "72b-text-q3_K_M", + "72b-text-v1.5-q3_K_M", + "72b-text-q3_K_L", + "72b-text-v1.5-q3_K_L", + "72b-text-q4_0", + "72b-text-v1.5-q4_0", + "72b-text-q4_1", + "72b-text-v1.5-q4_1", + "72b-text-q4_K_S", + "72b-text-v1.5-q4_K_S", + "72b-text-q4_K_M", + "72b-text-v1.5-q4_K_M", + "72b-text-q5_0", + "72b-text-v1.5-q5_0", + "72b-text-q5_1", + "72b-text-v1.5-q5_1", + "72b-text-q5_K_S", + "72b-text-v1.5-q5_K_S", + "72b-text-q5_K_M", + "72b-text-v1.5-q5_K_M", + "72b-text-q6_K", + "72b-text-v1.5-q6_K", + "72b-text-q8_0", + "72b-text-v1.5-q8_0", + "72b-text-fp16", + "72b-text-v1.5-fp16", + "110b-chat", + "110b-chat-v1.5-q2_K", + "110b-chat-v1.5-q3_K_S", + "110b-chat-v1.5-q3_K_M", + "110b-chat-v1.5-q3_K_L", + "110b-chat-v1.5-q4_0", + "110b-chat-v1.5-q4_1", + "110b-chat-v1.5-q4_K_S", + "110b-chat-v1.5-q4_K_M", + "110b-chat-v1.5-q5_0", + "110b-chat-v1.5-q5_1", + "110b-chat-v1.5-q5_K_S", + "110b-chat-v1.5-q5_K_M", + "110b-chat-v1.5-q6_K", + "110b-chat-v1.5-q8_0", + "110b-chat-v1.5-fp16", + "110b-text-v1.5-q2_K", + "110b-text-v1.5-q3_K_S", + "110b-text-v1.5-q3_K_M", + "110b-text-v1.5-q3_K_L", + "110b-text-v1.5-q4_0", + "110b-text-v1.5-q4_1", + "110b-text-v1.5-q4_K_S", + "110b-text-v1.5-q4_K_M", + "110b-text-v1.5-q5_0", + "110b-text-v1.5-q5_1", + "110b-text-v1.5-q5_K_S", + "110b-text-v1.5-q5_K_M", + "110b-text-v1.5-q6_K", + "110b-text-v1.5-q8_0", + "110b-text-v1.5-fp16" + ], + "capabilities": [] + }, + "llama2": { + "tags": [ + "latest", + "chat", + "text", + "7b", + "13b", + "70b", + "7b-chat", + "7b-chat-q2_K", + "7b-chat-q3_K_S", + "7b-chat-q3_K_M", + "7b-chat-q3_K_L", + "7b-chat-q4_0", + "7b-chat-q4_1", + "7b-chat-q4_K_S", + "7b-chat-q4_K_M", + "7b-chat-q5_0", + "7b-chat-q5_1", + "7b-chat-q5_K_S", + "7b-chat-q5_K_M", + "7b-chat-q6_K", + "7b-chat-q8_0", + "7b-chat-fp16", + "7b-text", + "7b-text-q2_K", + "7b-text-q3_K_S", + "7b-text-q3_K_M", + "7b-text-q3_K_L", + "7b-text-q4_0", + "7b-text-q4_1", + "7b-text-q4_K_S", + "7b-text-q4_K_M", + "7b-text-q5_0", + "7b-text-q5_1", + "7b-text-q5_K_S", + "7b-text-q5_K_M", + "7b-text-q6_K", + "7b-text-q8_0", + "7b-text-fp16", + "13b-chat", + "13b-chat-q2_K", + "13b-chat-q3_K_S", + "13b-chat-q3_K_M", + "13b-chat-q3_K_L", + "13b-chat-q4_0", + "13b-chat-q4_1", + "13b-chat-q4_K_S", + "13b-chat-q4_K_M", + "13b-chat-q5_0", + "13b-chat-q5_1", + "13b-chat-q5_K_S", + "13b-chat-q5_K_M", + "13b-chat-q6_K", + "13b-chat-q8_0", + "13b-chat-fp16", + "13b-text", + "13b-text-q2_K", + "13b-text-q3_K_S", + "13b-text-q3_K_M", + "13b-text-q3_K_L", + "13b-text-q4_0", + "13b-text-q4_1", + "13b-text-q4_K_S", + "13b-text-q4_K_M", + "13b-text-q5_0", + "13b-text-q5_1", + "13b-text-q5_K_S", + "13b-text-q5_K_M", + "13b-text-q6_K", + "13b-text-q8_0", + "13b-text-fp16", + "70b-chat", + "70b-chat-q2_K", + "70b-chat-q3_K_S", + "70b-chat-q3_K_M", + "70b-chat-q3_K_L", + "70b-chat-q4_0", + "70b-chat-q4_1", + "70b-chat-q4_K_S", + "70b-chat-q4_K_M", + "70b-chat-q5_0", + "70b-chat-q5_1", + "70b-chat-q5_K_S", + "70b-chat-q5_K_M", + "70b-chat-q6_K", + "70b-chat-q8_0", + "70b-chat-fp16", + "70b-text", + "70b-text-q2_K", + "70b-text-q3_K_S", + "70b-text-q3_K_M", + "70b-text-q3_K_L", + "70b-text-q4_0", + "70b-text-q4_1", + "70b-text-q4_K_S", + "70b-text-q4_K_M", + "70b-text-q5_0", + "70b-text-q5_1", + "70b-text-q5_K_S", + "70b-text-q5_K_M", + "70b-text-q6_K", + "70b-text-q8_0", + "70b-text-fp16" + ], + "capabilities": [] + }, + "qwen2": { + "tags": [ + "latest", + "0.5b", + "1.5b", + "7b", + "72b", + "0.5b-instruct", + "0.5b-instruct-q2_K", + "0.5b-instruct-q3_K_S", + "0.5b-instruct-q3_K_M", + "0.5b-instruct-q3_K_L", + "0.5b-instruct-q4_0", + "0.5b-instruct-q4_1", + "0.5b-instruct-q4_K_S", + "0.5b-instruct-q4_K_M", + "0.5b-instruct-q5_0", + "0.5b-instruct-q5_1", + "0.5b-instruct-q5_K_S", + "0.5b-instruct-q5_K_M", + "0.5b-instruct-q6_K", + "0.5b-instruct-q8_0", + "0.5b-instruct-fp16", + "1.5b-instruct", + "1.5b-instruct-q2_K", + "1.5b-instruct-q3_K_S", + "1.5b-instruct-q3_K_M", + "1.5b-instruct-q3_K_L", + "1.5b-instruct-q4_0", + "1.5b-instruct-q4_1", + "1.5b-instruct-q4_K_S", + "1.5b-instruct-q4_K_M", + "1.5b-instruct-q5_0", + "1.5b-instruct-q5_1", + "1.5b-instruct-q5_K_S", + "1.5b-instruct-q5_K_M", + "1.5b-instruct-q6_K", + "1.5b-instruct-q8_0", + "1.5b-instruct-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "7b-text", + "7b-text-q2_K", + "7b-text-q3_K_S", + "7b-text-q3_K_M", + "7b-text-q3_K_L", + "7b-text-q4_0", + "7b-text-q4_1", + "7b-text-q4_K_S", + "7b-text-q4_K_M", + "7b-text-q5_0", + "7b-text-q5_1", + "7b-text-q8_0", + "72b-instruct", + "72b-instruct-q2_K", + "72b-instruct-q3_K_S", + "72b-instruct-q3_K_M", + "72b-instruct-q3_K_L", + "72b-instruct-q4_0", + "72b-instruct-q4_1", + "72b-instruct-q4_K_S", + "72b-instruct-q4_K_M", + "72b-instruct-q5_0", + "72b-instruct-q5_1", + "72b-instruct-q5_K_S", + "72b-instruct-q5_K_M", + "72b-instruct-q6_K", + "72b-instruct-q8_0", + "72b-instruct-fp16", + "72b-text", + "72b-text-q2_K", + "72b-text-q3_K_S", + "72b-text-q3_K_M", + "72b-text-q3_K_L", + "72b-text-q4_0", + "72b-text-q4_1", + "72b-text-q4_K_S", + "72b-text-q4_K_M", + "72b-text-q5_0", + "72b-text-q5_1", + "72b-text-q5_K_S", + "72b-text-q5_K_M", + "72b-text-q6_K", + "72b-text-q8_0", + "72b-text-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "minicpm-v": { + "tags": [ + "latest", + "8b", + "8b-2.6-q2_K", + "8b-2.6-q3_K_S", + "8b-2.6-q3_K_M", + "8b-2.6-q3_K_L", + "8b-2.6-q4_0", + "8b-2.6-q4_1", + "8b-2.6-q4_K_S", + "8b-2.6-q4_K_M", + "8b-2.6-q5_0", + "8b-2.6-q5_1", + "8b-2.6-q5_K_S", + "8b-2.6-q5_K_M", + "8b-2.6-q6_K", + "8b-2.6-q8_0", + "8b-2.6-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "codellama": { + "tags": [ + "latest", + "code", + "instruct", + "python", + "7b", + "13b", + "34b", + "70b", + "7b-code", + "7b-code-q2_K", + "7b-code-q3_K_S", + "7b-code-q3_K_M", + "7b-code-q3_K_L", + "7b-code-q4_0", + "7b-code-q4_1", + "7b-code-q4_K_S", + "7b-code-q4_K_M", + "7b-code-q5_0", + "7b-code-q5_1", + "7b-code-q5_K_S", + "7b-code-q5_K_M", + "7b-code-q6_K", + "7b-code-q8_0", + "7b-code-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "7b-python", + "7b-python-q2_K", + "7b-python-q3_K_S", + "7b-python-q3_K_M", + "7b-python-q3_K_L", + "7b-python-q4_0", + "7b-python-q4_1", + "7b-python-q4_K_S", + "7b-python-q4_K_M", + "7b-python-q5_0", + "7b-python-q5_1", + "7b-python-q5_K_S", + "7b-python-q5_K_M", + "7b-python-q6_K", + "7b-python-q8_0", + "7b-python-fp16", + "13b-code", + "13b-code-q2_K", + "13b-code-q3_K_S", + "13b-code-q3_K_M", + "13b-code-q3_K_L", + "13b-code-q4_0", + "13b-code-q4_1", + "13b-code-q4_K_S", + "13b-code-q4_K_M", + "13b-code-q5_0", + "13b-code-q5_1", + "13b-code-q5_K_S", + "13b-code-q5_K_M", + "13b-code-q6_K", + "13b-code-q8_0", + "13b-code-fp16", + "13b-instruct", + "13b-instruct-q2_K", + "13b-instruct-q3_K_S", + "13b-instruct-q3_K_M", + "13b-instruct-q3_K_L", + "13b-instruct-q4_0", + "13b-instruct-q4_1", + "13b-instruct-q4_K_S", + "13b-instruct-q4_K_M", + "13b-instruct-q5_0", + "13b-instruct-q5_1", + "13b-instruct-q5_K_S", + "13b-instruct-q5_K_M", + "13b-instruct-q6_K", + "13b-instruct-q8_0", + "13b-instruct-fp16", + "13b-python", + "13b-python-q2_K", + "13b-python-q3_K_S", + "13b-python-q3_K_M", + "13b-python-q3_K_L", + "13b-python-q4_0", + "13b-python-q4_1", + "13b-python-q4_K_S", + "13b-python-q4_K_M", + "13b-python-q5_0", + "13b-python-q5_1", + "13b-python-q5_K_S", + "13b-python-q5_K_M", + "13b-python-q6_K", + "13b-python-q8_0", + "13b-python-fp16", + "34b-code", + "34b-code-q2_K", + "34b-code-q3_K_S", + "34b-code-q3_K_M", + "34b-code-q3_K_L", + "34b-code-q4_0", + "34b-code-q4_1", + "34b-code-q4_K_S", + "34b-code-q4_K_M", + "34b-code-q5_0", + "34b-code-q5_1", + "34b-code-q5_K_S", + "34b-code-q5_K_M", + "34b-code-q6_K", + "34b-code-q8_0", + "34b-instruct", + "34b-instruct-q2_K", + "34b-instruct-q3_K_S", + "34b-instruct-q3_K_M", + "34b-instruct-q3_K_L", + "34b-instruct-q4_0", + "34b-instruct-q4_1", + "34b-instruct-q4_K_S", + "34b-instruct-q4_K_M", + "34b-instruct-q5_0", + "34b-instruct-q5_1", + "34b-instruct-q5_K_S", + "34b-instruct-q5_K_M", + "34b-instruct-q6_K", + "34b-instruct-q8_0", + "34b-instruct-fp16", + "34b-python", + "34b-python-q2_K", + "34b-python-q3_K_S", + "34b-python-q3_K_M", + "34b-python-q3_K_L", + "34b-python-q4_0", + "34b-python-q4_1", + "34b-python-q4_K_S", + "34b-python-q4_K_M", + "34b-python-q5_0", + "34b-python-q5_1", + "34b-python-q5_K_S", + "34b-python-q5_K_M", + "34b-python-q6_K", + "34b-python-q8_0", + "34b-python-fp16", + "70b-code", + "70b-code-q2_K", + "70b-code-q3_K_S", + "70b-code-q3_K_M", + "70b-code-q3_K_L", + "70b-code-q4_0", + "70b-code-q4_1", + "70b-code-q4_K_S", + "70b-code-q4_K_M", + "70b-code-q5_0", + "70b-code-q5_1", + "70b-code-q5_K_S", + "70b-code-q5_K_M", + "70b-code-q6_K", + "70b-code-q8_0", + "70b-code-fp16", + "70b-instruct", + "70b-instruct-q2_K", + "70b-instruct-q3_K_S", + "70b-instruct-q3_K_M", + "70b-instruct-q3_K_L", + "70b-instruct-q4_0", + "70b-instruct-q4_1", + "70b-instruct-q4_K_S", + "70b-instruct-q4_K_M", + "70b-instruct-q5_0", + "70b-instruct-q5_1", + "70b-instruct-q5_K_S", + "70b-instruct-q5_K_M", + "70b-instruct-q6_K", + "70b-instruct-q8_0", + "70b-instruct-fp16", + "70b-python", + "70b-python-q2_K", + "70b-python-q3_K_S", + "70b-python-q3_K_M", + "70b-python-q3_K_L", + "70b-python-q4_0", + "70b-python-q4_1", + "70b-python-q4_K_S", + "70b-python-q4_K_M", + "70b-python-q5_0", + "70b-python-q5_1", + "70b-python-q5_K_S", + "70b-python-q5_K_M", + "70b-python-q6_K", + "70b-python-q8_0", + "70b-python-fp16" + ], + "capabilities": [] + }, + "llama3.2-vision": { + "tags": [ + "latest", + "11b", + "90b", + "11b-instruct-q4_K_M", + "11b-instruct-q8_0", + "11b-instruct-fp16", + "90b-instruct-q4_K_M", + "90b-instruct-q8_0", + "90b-instruct-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "dolphin3": { + "tags": [ + "latest", + "8b", + "8b-llama3.1-q4_K_M", + "8b-llama3.1-q8_0", + "8b-llama3.1-fp16" + ], + "capabilities": [] + }, + "olmo2": { + "tags": [ + "latest", + "7b", + "13b", + "7b-1124-instruct-q4_K_M", + "7b-1124-instruct-q8_0", + "7b-1124-instruct-fp16", + "13b-1124-instruct-q4_K_M", + "13b-1124-instruct-q8_0", + "13b-1124-instruct-fp16" + ], + "capabilities": [] + }, + "tinyllama": { + "tags": [ + "latest", + "chat", + "v0.6", + "v1", + "1.1b", + "1.1b-chat", + "1.1b-chat-v0.6-q2_K", + "1.1b-chat-v0.6-q3_K_S", + "1.1b-chat-v0.6-q3_K_M", + "1.1b-chat-v0.6-q3_K_L", + "1.1b-chat-v0.6-q4_0", + "1.1b-chat-v0.6-q4_1", + "1.1b-chat-v0.6-q4_K_S", + "1.1b-chat-v0.6-q4_K_M", + "1.1b-chat-v0.6-q5_0", + "1.1b-chat-v0.6-q5_1", + "1.1b-chat-v0.6-q5_K_S", + "1.1b-chat-v0.6-q5_K_M", + "1.1b-chat-v0.6-q6_K", + "1.1b-chat-v0.6-q8_0", + "1.1b-chat-v0.6-fp16", + "1.1b-chat-v1-q2_K", + "1.1b-chat-v1-q3_K_S", + "1.1b-chat-v1-q3_K_M", + "1.1b-chat-v1-q3_K_L", + "1.1b-chat-v1-q4_0", + "1.1b-chat-v1-q4_1", + "1.1b-chat-v1-q4_K_S", + "1.1b-chat-v1-q4_K_M", + "1.1b-chat-v1-q5_0", + "1.1b-chat-v1-q5_1", + "1.1b-chat-v1-q5_K_S", + "1.1b-chat-v1-q5_K_M", + "1.1b-chat-v1-q6_K", + "1.1b-chat-v1-q8_0", + "1.1b-chat-v1-fp16" + ], + "capabilities": [] + }, + "mistral-nemo": { + "tags": [ + "latest", + "12b", + "12b-instruct-2407-q2_K", + "12b-instruct-2407-q3_K_S", + "12b-instruct-2407-q3_K_M", + "12b-instruct-2407-q3_K_L", + "12b-instruct-2407-q4_0", + "12b-instruct-2407-q4_1", + "12b-instruct-2407-q4_K_S", + "12b-instruct-2407-q4_K_M", + "12b-instruct-2407-q5_0", + "12b-instruct-2407-q5_1", + "12b-instruct-2407-q5_K_S", + "12b-instruct-2407-q5_K_M", + "12b-instruct-2407-q6_K", + "12b-instruct-2407-q8_0", + "12b-instruct-2407-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "deepseek-v3": { + "tags": [ + "latest", + "671b", + "671b-q4_K_M", + "671b-q8_0", + "671b-fp16" + ], + "capabilities": [] + }, + "bge-m3": { + "tags": [ + "latest", + "567m", + "567m-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "llama3.3": { + "tags": [ + "latest", + "70b", + "70b-instruct-q2_K", + "70b-instruct-q3_K_S", + "70b-instruct-q3_K_M", + "70b-instruct-q4_0", + "70b-instruct-q4_K_S", + "70b-instruct-q4_K_M", + "70b-instruct-q5_0", + "70b-instruct-q5_1", + "70b-instruct-q5_K_M", + "70b-instruct-q6_K", + "70b-instruct-q8_0", + "70b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "deepseek-coder": { + "tags": [ + "latest", + "base", + "instruct", + "1.3b", + "6.7b", + "33b", + "1.3b-base", + "1.3b-base-q2_K", + "1.3b-base-q3_K_S", + "1.3b-base-q3_K_M", + "1.3b-base-q3_K_L", + "1.3b-base-q4_0", + "1.3b-base-q4_1", + "1.3b-base-q4_K_S", + "1.3b-base-q4_K_M", + "1.3b-base-q5_0", + "1.3b-base-q5_1", + "1.3b-base-q5_K_S", + "1.3b-base-q5_K_M", + "1.3b-base-q6_K", + "1.3b-base-q8_0", + "1.3b-base-fp16", + "1.3b-instruct", + "1.3b-instruct-q2_K", + "1.3b-instruct-q3_K_S", + "1.3b-instruct-q3_K_M", + "1.3b-instruct-q3_K_L", + "1.3b-instruct-q4_0", + "1.3b-instruct-q4_1", + "1.3b-instruct-q4_K_S", + "1.3b-instruct-q4_K_M", + "1.3b-instruct-q5_0", + "1.3b-instruct-q5_1", + "1.3b-instruct-q5_K_S", + "1.3b-instruct-q5_K_M", + "1.3b-instruct-q6_K", + "1.3b-instruct-q8_0", + "1.3b-instruct-fp16", + "6.7b-base", + "6.7b-base-q2_K", + "6.7b-base-q3_K_S", + "6.7b-base-q3_K_M", + "6.7b-base-q3_K_L", + "6.7b-base-q4_0", + "6.7b-base-q4_1", + "6.7b-base-q4_K_S", + "6.7b-base-q4_K_M", + "6.7b-base-q5_0", + "6.7b-base-q5_1", + "6.7b-base-q5_K_S", + "6.7b-base-q5_K_M", + "6.7b-base-q6_K", + "6.7b-base-q8_0", + "6.7b-base-fp16", + "6.7b-instruct", + "6.7b-instruct-q2_K", + "6.7b-instruct-q3_K_S", + "6.7b-instruct-q3_K_M", + "6.7b-instruct-q3_K_L", + "6.7b-instruct-q4_0", + "6.7b-instruct-q4_1", + "6.7b-instruct-q4_K_S", + "6.7b-instruct-q4_K_M", + "6.7b-instruct-q5_0", + "6.7b-instruct-q5_1", + "6.7b-instruct-q5_K_S", + "6.7b-instruct-q5_K_M", + "6.7b-instruct-q6_K", + "6.7b-instruct-q8_0", + "6.7b-instruct-fp16", + "33b-base", + "33b-base-q2_K", + "33b-base-q3_K_S", + "33b-base-q3_K_M", + "33b-base-q3_K_L", + "33b-base-q4_0", + "33b-base-q4_1", + "33b-base-q4_K_S", + "33b-base-q4_K_M", + "33b-base-q5_0", + "33b-base-q5_1", + "33b-base-q5_K_S", + "33b-base-q5_K_M", + "33b-base-q6_K", + "33b-base-q8_0", + "33b-base-fp16", + "33b-instruct", + "33b-instruct-q2_K", + "33b-instruct-q3_K_S", + "33b-instruct-q3_K_M", + "33b-instruct-q3_K_L", + "33b-instruct-q4_0", + "33b-instruct-q4_1", + "33b-instruct-q4_K_S", + "33b-instruct-q4_K_M", + "33b-instruct-q5_0", + "33b-instruct-q5_1", + "33b-instruct-q5_K_S", + "33b-instruct-q5_K_M", + "33b-instruct-q6_K", + "33b-instruct-q8_0", + "33b-instruct-fp16" + ], + "capabilities": [] + }, + "smollm2": { + "tags": [ + "latest", + "135m", + "360m", + "1.7b", + "135m-instruct-q2_K", + "135m-instruct-q3_K_S", + "135m-instruct-q3_K_M", + "135m-instruct-q3_K_L", + "135m-instruct-q4_0", + "135m-instruct-q4_1", + "135m-instruct-q4_K_S", + "135m-instruct-q4_K_M", + "135m-instruct-q5_0", + "135m-instruct-q5_1", + "135m-instruct-q5_K_S", + "135m-instruct-q5_K_M", + "135m-instruct-q6_K", + "135m-instruct-q8_0", + "135m-instruct-fp16", + "360m-instruct-q2_K", + "360m-instruct-q3_K_S", + "360m-instruct-q3_K_M", + "360m-instruct-q3_K_L", + "360m-instruct-q4_0", + "360m-instruct-q4_1", + "360m-instruct-q4_K_S", + "360m-instruct-q4_K_M", + "360m-instruct-q5_0", + "360m-instruct-q5_1", + "360m-instruct-q5_K_S", + "360m-instruct-q5_K_M", + "360m-instruct-q6_K", + "360m-instruct-q8_0", + "360m-instruct-fp16", + "1.7b-instruct-q2_K", + "1.7b-instruct-q3_K_S", + "1.7b-instruct-q3_K_M", + "1.7b-instruct-q3_K_L", + "1.7b-instruct-q4_0", + "1.7b-instruct-q4_1", + "1.7b-instruct-q4_K_S", + "1.7b-instruct-q4_K_M", + "1.7b-instruct-q5_0", + "1.7b-instruct-q5_1", + "1.7b-instruct-q5_K_S", + "1.7b-instruct-q5_K_M", + "1.7b-instruct-q6_K", + "1.7b-instruct-q8_0", + "1.7b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "mistral-small": { + "tags": [ + "latest", + "22b", + "24b", + "22b-instruct-2409-q2_K", + "22b-instruct-2409-q3_K_S", + "22b-instruct-2409-q3_K_M", + "22b-instruct-2409-q3_K_L", + "22b-instruct-2409-q4_0", + "22b-instruct-2409-q4_1", + "22b-instruct-2409-q4_K_S", + "22b-instruct-2409-q4_K_M", + "22b-instruct-2409-q5_0", + "22b-instruct-2409-q5_1", + "22b-instruct-2409-q5_K_S", + "22b-instruct-2409-q5_K_M", + "22b-instruct-2409-q6_K", + "22b-instruct-2409-q8_0", + "22b-instruct-2409-fp16", + "24b-instruct-2501-q4_K_M", + "24b-instruct-2501-q8_0", + "24b-instruct-2501-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "all-minilm": { + "tags": [ + "latest", + "l12", + "l6", + "v2", + "22m", + "33m", + "22m-l6-v2-fp16", + "33m-l12-v2-fp16", + "l12-v2", + "l6-v2" + ], + "capabilities": [ + "embedding" + ] + }, + "llava-llama3": { + "tags": [ + "latest", + "8b", + "8b-v1.1-q4_0", + "8b-v1.1-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "qwq": { + "tags": [ + "latest", + "32b", + "32b-preview-q4_K_M", + "32b-preview-q8_0", + "32b-preview-fp16", + "32b-q4_K_M", + "32b-q8_0", + "32b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "codegemma": { + "tags": [ + "latest", + "code", + "instruct", + "2b", + "7b", + "2b-code", + "2b-code-q2_K", + "2b-code-v1.1-q2_K", + "2b-code-q3_K_S", + "2b-code-v1.1-q3_K_S", + "2b-code-q3_K_M", + "2b-code-v1.1-q3_K_M", + "2b-code-q3_K_L", + "2b-code-v1.1-q3_K_L", + "2b-code-q4_0", + "2b-code-v1.1-q4_0", + "2b-code-q4_1", + "2b-code-v1.1-q4_1", + "2b-code-q4_K_S", + "2b-code-v1.1-q4_K_S", + "2b-code-q4_K_M", + "2b-code-v1.1-q4_K_M", + "2b-code-q5_0", + "2b-code-v1.1-q5_0", + "2b-code-q5_1", + "2b-code-v1.1-q5_1", + "2b-code-q5_K_S", + "2b-code-v1.1-q5_K_S", + "2b-code-q5_K_M", + "2b-code-v1.1-q5_K_M", + "2b-code-q6_K", + "2b-code-v1.1-q6_K", + "2b-code-q8_0", + "2b-code-v1.1-q8_0", + "2b-code-fp16", + "2b-code-v1.1-fp16", + "2b-v1.1", + "7b-code", + "7b-code-q2_K", + "7b-code-q3_K_S", + "7b-code-q3_K_M", + "7b-code-q3_K_L", + "7b-code-q4_0", + "7b-code-q4_1", + "7b-code-q4_K_S", + "7b-code-q4_K_M", + "7b-code-q5_0", + "7b-code-q5_1", + "7b-code-q5_K_S", + "7b-code-q5_K_M", + "7b-code-q6_K", + "7b-code-q8_0", + "7b-code-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-v1.1-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-v1.1-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-v1.1-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-v1.1-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-v1.1-q4_0", + "7b-instruct-q4_1", + "7b-instruct-v1.1-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-v1.1-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-v1.1-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-v1.1-q5_0", + "7b-instruct-q5_1", + "7b-instruct-v1.1-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-v1.1-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-v1.1-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-v1.1-q6_K", + "7b-instruct-q8_0", + "7b-instruct-v1.1-q8_0", + "7b-instruct-fp16", + "7b-instruct-v1.1-fp16", + "7b-v1.1" + ], + "capabilities": [] + }, + "granite3.1-moe": { + "tags": [ + "latest", + "1b", + "3b", + "1b-instruct-q2_K", + "1b-instruct-q3_K_S", + "1b-instruct-q3_K_M", + "1b-instruct-q3_K_L", + "1b-instruct-q4_0", + "1b-instruct-q4_1", + "1b-instruct-q4_K_S", + "1b-instruct-q4_K_M", + "1b-instruct-q5_0", + "1b-instruct-q5_1", + "1b-instruct-q5_K_S", + "1b-instruct-q5_K_M", + "1b-instruct-q6_K", + "1b-instruct-q8_0", + "1b-instruct-fp16", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "falcon3": { + "tags": [ + "latest", + "1b", + "3b", + "7b", + "10b", + "1b-instruct-q4_K_M", + "1b-instruct-q8_0", + "1b-instruct-fp16", + "3b-instruct-q4_K_M", + "3b-instruct-q8_0", + "3b-instruct-fp16", + "7b-instruct-q4_K_M", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "10b-instruct-q4_K_M", + "10b-instruct-q8_0", + "10b-instruct-fp16" + ], + "capabilities": [] + }, + "starcoder2": { + "tags": [ + "latest", + "instruct", + "3b", + "7b", + "15b", + "3b-q2_K", + "3b-q3_K_S", + "3b-q3_K_M", + "3b-q3_K_L", + "3b-q4_0", + "3b-q4_1", + "3b-q4_K_S", + "3b-q4_K_M", + "3b-q5_0", + "3b-q5_1", + "3b-q5_K_S", + "3b-q5_K_M", + "3b-q6_K", + "3b-q8_0", + "3b-fp16", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "15b-instruct", + "15b-instruct-v0.1-q2_K", + "15b-instruct-v0.1-q3_K_S", + "15b-instruct-v0.1-q3_K_M", + "15b-instruct-v0.1-q3_K_L", + "15b-instruct-q4_0", + "15b-instruct-v0.1-q4_0", + "15b-instruct-v0.1-q4_1", + "15b-instruct-v0.1-q4_K_S", + "15b-instruct-v0.1-q4_K_M", + "15b-instruct-v0.1-q5_0", + "15b-instruct-v0.1-q5_1", + "15b-instruct-v0.1-q5_K_S", + "15b-instruct-v0.1-q5_K_M", + "15b-instruct-v0.1-q6_K", + "15b-instruct-v0.1-q8_0", + "15b-instruct-v0.1-fp16", + "15b-q2_K", + "15b-q3_K_S", + "15b-q3_K_M", + "15b-q3_K_L", + "15b-q4_0", + "15b-q4_1", + "15b-q4_K_S", + "15b-q4_K_M", + "15b-q5_0", + "15b-q5_1", + "15b-q5_K_S", + "15b-q5_K_M", + "15b-q6_K", + "15b-q8_0", + "15b-fp16" + ], + "capabilities": [] + }, + "snowflake-arctic-embed": { + "tags": [ + "latest", + "l", + "m", + "s", + "xs", + "22m", + "33m", + "110m", + "137m", + "335m", + "22m-xs-fp16", + "33m-s-fp16", + "110m-m-fp16", + "137m-m-long-fp16", + "335m-l-fp16", + "m-long" + ], + "capabilities": [ + "embedding" + ] + }, + "orca-mini": { + "tags": [ + "latest", + "3b", + "7b", + "13b", + "70b", + "3b-q4_0", + "3b-q4_1", + "3b-q5_0", + "3b-q5_1", + "3b-q8_0", + "3b-fp16", + "7b-v2-q2_K", + "7b-v2-q3_K_S", + "7b-v2-q3_K_M", + "7b-v2-q3_K_L", + "7b-v2-q4_0", + "7b-v2-q4_1", + "7b-v2-q4_K_S", + "7b-v2-q4_K_M", + "7b-v2-q5_0", + "7b-v2-q5_1", + "7b-v2-q5_K_S", + "7b-v2-q5_K_M", + "7b-v2-q6_K", + "7b-v2-q8_0", + "7b-v2-fp16", + "7b-v3", + "7b-v3-q2_K", + "7b-v3-q3_K_S", + "7b-v3-q3_K_M", + "7b-v3-q3_K_L", + "7b-v3-q4_0", + "7b-v3-q4_1", + "7b-v3-q4_K_S", + "7b-v3-q4_K_M", + "7b-v3-q5_0", + "7b-v3-q5_1", + "7b-v3-q5_K_S", + "7b-v3-q5_K_M", + "7b-v3-q6_K", + "7b-v3-q8_0", + "7b-v3-fp16", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-v2-q2_K", + "13b-v2-q3_K_S", + "13b-v2-q3_K_M", + "13b-v2-q3_K_L", + "13b-v2-q4_0", + "13b-v2-q4_1", + "13b-v2-q4_K_S", + "13b-v2-q4_K_M", + "13b-v2-q5_0", + "13b-v2-q5_1", + "13b-v2-q5_K_S", + "13b-v2-q5_K_M", + "13b-v2-q6_K", + "13b-v2-q8_0", + "13b-v2-fp16", + "13b-v3", + "13b-v3-q2_K", + "13b-v3-q3_K_S", + "13b-v3-q3_K_M", + "13b-v3-q3_K_L", + "13b-v3-q4_0", + "13b-v3-q4_1", + "13b-v3-q4_K_S", + "13b-v3-q4_K_M", + "13b-v3-q5_0", + "13b-v3-q5_1", + "13b-v3-q5_K_S", + "13b-v3-q5_K_M", + "13b-v3-q6_K", + "13b-v3-q8_0", + "13b-v3-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "70b-v3", + "70b-v3-q2_K", + "70b-v3-q3_K_S", + "70b-v3-q3_K_M", + "70b-v3-q3_K_L", + "70b-v3-q4_0", + "70b-v3-q4_1", + "70b-v3-q4_K_S", + "70b-v3-q4_K_M", + "70b-v3-q5_0", + "70b-v3-q5_1", + "70b-v3-q5_K_S", + "70b-v3-q5_K_M", + "70b-v3-q6_K", + "70b-v3-q8_0", + "70b-v3-fp16" + ], + "capabilities": [] + }, + "mixtral": { + "tags": [ + "latest", + "instruct", + "text", + "v0.1", + "8x7b", + "8x22b", + "8x7b-instruct-v0.1-q2_K", + "8x7b-instruct-v0.1-q3_K_S", + "8x7b-instruct-v0.1-q3_K_M", + "8x7b-instruct-v0.1-q3_K_L", + "8x7b-instruct-v0.1-q4_0", + "8x7b-instruct-v0.1-q4_1", + "8x7b-instruct-v0.1-q4_K_S", + "8x7b-instruct-v0.1-q4_K_M", + "8x7b-instruct-v0.1-q5_0", + "8x7b-instruct-v0.1-q5_1", + "8x7b-instruct-v0.1-q5_K_S", + "8x7b-instruct-v0.1-q5_K_M", + "8x7b-instruct-v0.1-q6_K", + "8x7b-instruct-v0.1-q8_0", + "8x7b-instruct-v0.1-fp16", + "8x7b-text", + "8x7b-text-v0.1-q2_K", + "8x7b-text-v0.1-q3_K_S", + "8x7b-text-v0.1-q3_K_M", + "8x7b-text-v0.1-q3_K_L", + "8x7b-text-v0.1-q4_0", + "8x7b-text-v0.1-q4_1", + "8x7b-text-v0.1-q4_K_S", + "8x7b-text-v0.1-q4_K_M", + "8x7b-text-v0.1-q5_0", + "8x7b-text-v0.1-q5_1", + "8x7b-text-v0.1-q5_K_S", + "8x7b-text-v0.1-q5_K_M", + "8x7b-text-v0.1-q6_K", + "8x7b-text-v0.1-q8_0", + "8x7b-text-v0.1-fp16", + "8x22b-instruct", + "8x22b-instruct-v0.1-q2_K", + "8x22b-instruct-v0.1-q3_K_S", + "8x22b-instruct-v0.1-q3_K_M", + "8x22b-instruct-v0.1-q3_K_L", + "8x22b-instruct-v0.1-q4_0", + "8x22b-instruct-v0.1-q4_1", + "8x22b-instruct-v0.1-q4_K_S", + "8x22b-instruct-v0.1-q4_K_M", + "8x22b-instruct-v0.1-q5_0", + "8x22b-instruct-v0.1-q5_1", + "8x22b-instruct-v0.1-q5_K_S", + "8x22b-instruct-v0.1-q5_K_M", + "8x22b-instruct-v0.1-q6_K", + "8x22b-instruct-v0.1-q8_0", + "8x22b-instruct-v0.1-fp16", + "8x22b-text", + "8x22b-text-v0.1-q2_K", + "8x22b-text-v0.1-q3_K_S", + "8x22b-text-v0.1-q3_K_M", + "8x22b-text-v0.1-q3_K_L", + "8x22b-text-v0.1-q4_0", + "8x22b-text-v0.1-q4_1", + "8x22b-text-v0.1-q4_K_S", + "8x22b-text-v0.1-q4_K_M", + "8x22b-text-v0.1-q5_0", + "8x22b-text-v0.1-q5_1", + "8x22b-text-v0.1-q5_K_S", + "8x22b-text-v0.1-q5_K_M", + "8x22b-text-v0.1-q6_K", + "8x22b-text-v0.1-q8_0", + "8x22b-text-v0.1-fp16", + "v0.1-instruct" + ], + "capabilities": [ + "tools" + ] + }, + "llama2-uncensored": { + "tags": [ + "latest", + "7b", + "70b", + "7b-chat", + "7b-chat-q2_K", + "7b-chat-q3_K_S", + "7b-chat-q3_K_M", + "7b-chat-q3_K_L", + "7b-chat-q4_0", + "7b-chat-q4_1", + "7b-chat-q4_K_S", + "7b-chat-q4_K_M", + "7b-chat-q5_0", + "7b-chat-q5_1", + "7b-chat-q5_K_S", + "7b-chat-q5_K_M", + "7b-chat-q6_K", + "7b-chat-q8_0", + "7b-chat-fp16", + "70b-chat", + "70b-chat-q2_K", + "70b-chat-q3_K_S", + "70b-chat-q3_K_M", + "70b-chat-q3_K_L", + "70b-chat-q4_0", + "70b-chat-q4_1", + "70b-chat-q4_K_S", + "70b-chat-q4_K_M", + "70b-chat-q5_0", + "70b-chat-q5_1", + "70b-chat-q5_K_S", + "70b-chat-q5_K_M", + "70b-chat-q6_K", + "70b-chat-q8_0" + ], + "capabilities": [] + }, + "deepseek-coder-v2": { + "tags": [ + "latest", + "lite", + "16b", + "236b", + "16b-lite-base-q2_K", + "16b-lite-base-q3_K_S", + "16b-lite-base-q3_K_M", + "16b-lite-base-q3_K_L", + "16b-lite-base-q4_0", + "16b-lite-base-q4_1", + "16b-lite-base-q4_K_S", + "16b-lite-base-q4_K_M", + "16b-lite-base-q5_0", + "16b-lite-base-q5_1", + "16b-lite-base-q5_K_S", + "16b-lite-base-q5_K_M", + "16b-lite-base-q6_K", + "16b-lite-base-q8_0", + "16b-lite-base-fp16", + "16b-lite-instruct-q2_K", + "16b-lite-instruct-q3_K_S", + "16b-lite-instruct-q3_K_M", + "16b-lite-instruct-q3_K_L", + "16b-lite-instruct-q4_0", + "16b-lite-instruct-q4_1", + "16b-lite-instruct-q4_K_S", + "16b-lite-instruct-q4_K_M", + "16b-lite-instruct-q5_0", + "16b-lite-instruct-q5_1", + "16b-lite-instruct-q5_K_S", + "16b-lite-instruct-q5_K_M", + "16b-lite-instruct-q6_K", + "16b-lite-instruct-q8_0", + "16b-lite-instruct-fp16", + "236b-base-q2_K", + "236b-base-q3_K_S", + "236b-base-q3_K_M", + "236b-base-q3_K_L", + "236b-base-q4_0", + "236b-base-q4_1", + "236b-base-q4_K_S", + "236b-base-q4_K_M", + "236b-base-q5_0", + "236b-base-q5_1", + "236b-base-q5_K_S", + "236b-base-q5_K_M", + "236b-base-q6_K", + "236b-base-q8_0", + "236b-base-fp16", + "236b-instruct-q2_K", + "236b-instruct-q3_K_S", + "236b-instruct-q3_K_M", + "236b-instruct-q3_K_L", + "236b-instruct-q4_0", + "236b-instruct-q4_1", + "236b-instruct-q4_K_S", + "236b-instruct-q4_K_M", + "236b-instruct-q5_0", + "236b-instruct-q5_1", + "236b-instruct-q5_K_S", + "236b-instruct-q5_K_M", + "236b-instruct-q6_K", + "236b-instruct-q8_0", + "236b-instruct-fp16" + ], + "capabilities": [] + }, + "cogito": { + "tags": [ + "latest", + "3b", + "8b", + "14b", + "32b", + "70b", + "3b-v1-preview-llama-q4_K_M", + "3b-v1-preview-llama-q8_0", + "3b-v1-preview-llama-fp16", + "8b-v1-preview-llama-q4_K_M", + "8b-v1-preview-llama-q8_0", + "14b-v1-preview-qwen-q4_K_M", + "14b-v1-preview-qwen-q8_0", + "14b-v1-preview-qwen-fp16", + "32b-v1-preview-qwen-q4_K_M", + "32b-v1-preview-qwen-q8_0", + "32b-v1-preview-qwen-fp16", + "70b-v1-preview-llama-q4_K_M", + "70b-v1-preview-llama-q8_0", + "70b-v1-preview-llama-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "qwen2.5vl": { + "tags": [ + "latest", + "3b", + "7b", + "32b", + "72b", + "3b-q4_K_M", + "3b-q8_0", + "3b-fp16", + "7b-q4_K_M", + "7b-q8_0", + "7b-fp16", + "32b-q4_K_M", + "32b-q8_0", + "32b-fp16", + "72b-q4_K_M", + "72b-q8_0", + "72b-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "mistral-small3.2": { + "tags": [ + "latest", + "24b", + "24b-instruct-2506-q4_K_M", + "24b-instruct-2506-q8_0", + "24b-instruct-2506-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "dolphin-phi": { + "tags": [ + "latest", + "2.7b", + "2.7b-v2.6", + "2.7b-v2.6-q2_K", + "2.7b-v2.6-q3_K_S", + "2.7b-v2.6-q3_K_M", + "2.7b-v2.6-q3_K_L", + "2.7b-v2.6-q4_0", + "2.7b-v2.6-q4_K_S", + "2.7b-v2.6-q4_K_M", + "2.7b-v2.6-q5_0", + "2.7b-v2.6-q5_K_S", + "2.7b-v2.6-q5_K_M", + "2.7b-v2.6-q6_K", + "2.7b-v2.6-q8_0" + ], + "capabilities": [] + }, + "gemma3n": { + "tags": [ + "latest", + "e2b", + "e4b", + "e2b-it-q4_K_M", + "e2b-it-q8_0", + "e2b-it-fp16", + "e4b-it-q4_K_M", + "e4b-it-q8_0", + "e4b-it-fp16" + ], + "capabilities": [] + }, + "deepscaler": { + "tags": [ + "latest", + "1.5b", + "1.5b-preview-q4_K_M", + "1.5b-preview-q8_0", + "1.5b-preview-fp16" + ], + "capabilities": [] + }, + "llama4": { + "tags": [ + "latest", + "maverick", + "scout", + "16x17b", + "128x17b", + "17b-maverick-128e-instruct-q4_K_M", + "17b-maverick-128e-instruct-q8_0", + "17b-maverick-128e-instruct-fp16", + "17b-scout-16e-instruct-q4_K_M", + "17b-scout-16e-instruct-q8_0", + "17b-scout-16e-instruct-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "phi4-reasoning": { + "tags": [ + "latest", + "plus", + "14b", + "14b-plus-q4_K_M", + "14b-plus-q8_0", + "14b-plus-fp16", + "14b-q4_K_M", + "14b-q8_0", + "14b-fp16" + ], + "capabilities": [] + }, + "magistral": { + "tags": [ + "latest", + "24b", + "24b-small-2506-q4_K_M", + "24b-small-2506-q8_0", + "24b-small-2506-fp16" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "phi": { + "tags": [ + "latest", + "chat", + "2.7b", + "2.7b-chat-v2-q2_K", + "2.7b-chat-v2-q3_K_S", + "2.7b-chat-v2-q3_K_M", + "2.7b-chat-v2-q3_K_L", + "2.7b-chat-v2-q4_0", + "2.7b-chat-v2-q4_1", + "2.7b-chat-v2-q4_K_S", + "2.7b-chat-v2-q4_K_M", + "2.7b-chat-v2-q5_0", + "2.7b-chat-v2-q5_1", + "2.7b-chat-v2-q5_K_S", + "2.7b-chat-v2-q5_K_M", + "2.7b-chat-v2-q6_K", + "2.7b-chat-v2-q8_0", + "2.7b-chat-v2-fp16" + ], + "capabilities": [] + }, + "dolphin-mixtral": { + "tags": [ + "latest", + "v2.5", + "v2.6", + "v2.7", + "8x7b", + "8x22b", + "8x7b-v2.5", + "8x7b-v2.5-q2_K", + "8x7b-v2.5-q3_K_S", + "8x7b-v2.5-q3_K_M", + "8x7b-v2.5-q3_K_L", + "8x7b-v2.5-q4_0", + "8x7b-v2.5-q4_1", + "8x7b-v2.5-q4_K_S", + "8x7b-v2.5-q4_K_M", + "8x7b-v2.5-q5_0", + "8x7b-v2.5-q5_1", + "8x7b-v2.5-q5_K_S", + "8x7b-v2.5-q5_K_M", + "8x7b-v2.5-q6_K", + "8x7b-v2.5-q8_0", + "8x7b-v2.5-fp16", + "8x7b-v2.6", + "8x7b-v2.6-q2_K", + "8x7b-v2.6-q3_K_S", + "8x7b-v2.6-q3_K_M", + "8x7b-v2.6-q3_K_L", + "8x7b-v2.6-q4_0", + "8x7b-v2.6-q4_1", + "8x7b-v2.6-q4_K_S", + "8x7b-v2.6-q4_K_M", + "8x7b-v2.6-q5_0", + "8x7b-v2.6-q5_1", + "8x7b-v2.6-q5_K_S", + "8x7b-v2.6-q5_K_M", + "8x7b-v2.6-q6_K", + "8x7b-v2.6-q8_0", + "8x7b-v2.6-fp16", + "8x7b-v2.7", + "8x7b-v2.7-q2_K", + "8x7b-v2.7-q3_K_S", + "8x7b-v2.7-q3_K_M", + "8x7b-v2.7-q3_K_L", + "8x7b-v2.7-q4_0", + "8x7b-v2.7-q4_1", + "8x7b-v2.7-q4_K_S", + "8x7b-v2.7-q4_K_M", + "8x7b-v2.7-q5_0", + "8x7b-v2.7-q5_1", + "8x7b-v2.7-q5_K_S", + "8x7b-v2.7-q5_K_M", + "8x7b-v2.7-q6_K", + "8x7b-v2.7-q8_0", + "8x7b-v2.7-fp16", + "8x22b-v2.9", + "8x22b-v2.9-q2_K", + "8x22b-v2.9-q3_K_S", + "8x22b-v2.9-q3_K_M", + "8x22b-v2.9-q3_K_L", + "8x22b-v2.9-q4_0", + "8x22b-v2.9-q4_1", + "8x22b-v2.9-q4_K_S", + "8x22b-v2.9-q4_K_M", + "8x22b-v2.9-q5_0", + "8x22b-v2.9-q5_1", + "8x22b-v2.9-q5_K_S", + "8x22b-v2.9-q5_K_M", + "8x22b-v2.9-q6_K", + "8x22b-v2.9-q8_0", + "8x22b-v2.9-fp16" + ], + "capabilities": [] + }, + "granite3.3": { + "tags": [ + "latest", + "2b", + "8b" + ], + "capabilities": [ + "tools" + ] + }, + "dolphin-llama3": { + "tags": [ + "latest", + "v2.9", + "8b", + "70b", + "8b-256k", + "8b-256k-v2.9", + "8b-256k-v2.9-q2_K", + "8b-256k-v2.9-q3_K_S", + "8b-256k-v2.9-q3_K_M", + "8b-256k-v2.9-q3_K_L", + "8b-256k-v2.9-q4_0", + "8b-256k-v2.9-q4_1", + "8b-256k-v2.9-q4_K_S", + "8b-256k-v2.9-q4_K_M", + "8b-256k-v2.9-q5_0", + "8b-256k-v2.9-q5_1", + "8b-256k-v2.9-q5_K_S", + "8b-256k-v2.9-q5_K_M", + "8b-256k-v2.9-q6_K", + "8b-256k-v2.9-q8_0", + "8b-256k-v2.9-fp16", + "8b-v2.9", + "8b-v2.9-q2_K", + "8b-v2.9-q3_K_S", + "8b-v2.9-q3_K_M", + "8b-v2.9-q3_K_L", + "8b-v2.9-q4_0", + "8b-v2.9-q4_1", + "8b-v2.9-q4_K_S", + "8b-v2.9-q4_K_M", + "8b-v2.9-q5_0", + "8b-v2.9-q5_1", + "8b-v2.9-q5_K_S", + "8b-v2.9-q5_K_M", + "8b-v2.9-q6_K", + "8b-v2.9-q8_0", + "8b-v2.9-fp16", + "70b-v2.9", + "70b-v2.9-q2_K", + "70b-v2.9-q3_K_S", + "70b-v2.9-q3_K_M", + "70b-v2.9-q3_K_L", + "70b-v2.9-q4_0", + "70b-v2.9-q4_1", + "70b-v2.9-q4_K_S", + "70b-v2.9-q4_K_M", + "70b-v2.9-q5_0", + "70b-v2.9-q5_1", + "70b-v2.9-q5_K_S", + "70b-v2.9-q5_K_M", + "70b-v2.9-q6_K", + "70b-v2.9-q8_0", + "70b-v2.9-fp16" + ], + "capabilities": [] + }, + "phi4-mini": { + "tags": [ + "latest", + "3.8b", + "3.8b-q4_K_M", + "3.8b-q8_0", + "3.8b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "smollm": { + "tags": [ + "latest", + "135m", + "360m", + "1.7b", + "135m-base-v0.2-q2_K", + "135m-base-v0.2-q3_K_S", + "135m-base-v0.2-q3_K_M", + "135m-base-v0.2-q3_K_L", + "135m-base-v0.2-q4_0", + "135m-base-v0.2-q4_1", + "135m-base-v0.2-q4_K_S", + "135m-base-v0.2-q4_K_M", + "135m-base-v0.2-q5_0", + "135m-base-v0.2-q5_1", + "135m-base-v0.2-q5_K_S", + "135m-base-v0.2-q5_K_M", + "135m-base-v0.2-q6_K", + "135m-base-v0.2-q8_0", + "135m-base-v0.2-fp16", + "135m-instruct-v0.2-q2_K", + "135m-instruct-v0.2-q3_K_S", + "135m-instruct-v0.2-q3_K_M", + "135m-instruct-v0.2-q3_K_L", + "135m-instruct-v0.2-q4_0", + "135m-instruct-v0.2-q4_1", + "135m-instruct-v0.2-q4_K_S", + "135m-instruct-v0.2-q4_K_M", + "135m-instruct-v0.2-q5_0", + "135m-instruct-v0.2-q5_1", + "135m-instruct-v0.2-q5_K_S", + "135m-instruct-v0.2-q5_K_M", + "135m-instruct-v0.2-q6_K", + "135m-instruct-v0.2-q8_0", + "135m-instruct-v0.2-fp16", + "360m-base-v0.2-q2_K", + "360m-base-v0.2-q3_K_S", + "360m-base-v0.2-q3_K_M", + "360m-base-v0.2-q3_K_L", + "360m-base-v0.2-q4_0", + "360m-base-v0.2-q4_1", + "360m-base-v0.2-q4_K_S", + "360m-base-v0.2-q4_K_M", + "360m-base-v0.2-q5_0", + "360m-base-v0.2-q5_1", + "360m-base-v0.2-q5_K_S", + "360m-base-v0.2-q5_K_M", + "360m-base-v0.2-q6_K", + "360m-base-v0.2-q8_0", + "360m-base-v0.2-fp16", + "360m-instruct-v0.2-q2_K", + "360m-instruct-v0.2-q3_K_S", + "360m-instruct-v0.2-q3_K_M", + "360m-instruct-v0.2-q3_K_L", + "360m-instruct-v0.2-q4_0", + "360m-instruct-v0.2-q4_1", + "360m-instruct-v0.2-q4_K_S", + "360m-instruct-v0.2-q4_K_M", + "360m-instruct-v0.2-q5_0", + "360m-instruct-v0.2-q5_1", + "360m-instruct-v0.2-q5_K_S", + "360m-instruct-v0.2-q5_K_M", + "360m-instruct-v0.2-q6_K", + "360m-instruct-v0.2-q8_0", + "360m-instruct-v0.2-fp16", + "1.7b-base-v0.2-q2_K", + "1.7b-base-v0.2-q3_K_S", + "1.7b-base-v0.2-q3_K_M", + "1.7b-base-v0.2-q3_K_L", + "1.7b-base-v0.2-q4_0", + "1.7b-base-v0.2-q4_1", + "1.7b-base-v0.2-q4_K_S", + "1.7b-base-v0.2-q4_K_M", + "1.7b-base-v0.2-q5_0", + "1.7b-base-v0.2-q5_1", + "1.7b-base-v0.2-q5_K_S", + "1.7b-base-v0.2-q5_K_M", + "1.7b-base-v0.2-q6_K", + "1.7b-base-v0.2-q8_0", + "1.7b-base-v0.2-fp16", + "1.7b-instruct-v0.2-q2_K", + "1.7b-instruct-v0.2-q3_K_S", + "1.7b-instruct-v0.2-q3_K_M", + "1.7b-instruct-v0.2-q3_K_L", + "1.7b-instruct-v0.2-q4_0", + "1.7b-instruct-v0.2-q4_1", + "1.7b-instruct-v0.2-q4_K_S", + "1.7b-instruct-v0.2-q4_K_M", + "1.7b-instruct-v0.2-q5_0", + "1.7b-instruct-v0.2-q5_1", + "1.7b-instruct-v0.2-q5_K_S", + "1.7b-instruct-v0.2-q5_K_M", + "1.7b-instruct-v0.2-q6_K", + "1.7b-instruct-v0.2-q8_0", + "1.7b-instruct-v0.2-fp16" + ], + "capabilities": [] + }, + "openthinker": { + "tags": [ + "latest", + "7b", + "32b", + "7b-v2-q4_K_M", + "7b-v2-q8_0", + "7b-v2-fp16", + "7b-q4_K_M", + "7b-q8_0", + "7b-fp16", + "32b-v2-q4_K_M", + "32b-v2-q8_0", + "32b-v2-fp16", + "32b-q4_K_M", + "32b-q8_0", + "32b-fp16" + ], + "capabilities": [] + }, + "codestral": { + "tags": [ + "latest", + "v0.1", + "22b", + "22b-v0.1-q2_K", + "22b-v0.1-q3_K_S", + "22b-v0.1-q3_K_M", + "22b-v0.1-q3_K_L", + "22b-v0.1-q4_0", + "22b-v0.1-q4_1", + "22b-v0.1-q4_K_S", + "22b-v0.1-q4_K_M", + "22b-v0.1-q5_0", + "22b-v0.1-q5_1", + "22b-v0.1-q5_K_S", + "22b-v0.1-q5_K_M", + "22b-v0.1-q6_K", + "22b-v0.1-q8_0" + ], + "capabilities": [] + }, + "granite3.2-vision": { + "tags": [ + "latest", + "2b", + "2b-q4_K_M", + "2b-q8_0", + "2b-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "devstral": { + "tags": [ + "latest", + "24b", + "24b-small-2505-q4_K_M", + "24b-small-2505-q8_0", + "24b-small-2505-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "dolphin-mistral": { + "tags": [ + "latest", + "v2", + "v2.1", + "v2.2", + "v2.2.1", + "v2.6", + "v2.8", + "7b", + "7b-v2", + "7b-v2-q2_K", + "7b-v2-q3_K_S", + "7b-v2-q3_K_M", + "7b-v2-q3_K_L", + "7b-v2-q4_0", + "7b-v2-q4_1", + "7b-v2-q4_K_S", + "7b-v2-q4_K_M", + "7b-v2-q5_0", + "7b-v2-q5_1", + "7b-v2-q5_K_S", + "7b-v2-q5_K_M", + "7b-v2-q6_K", + "7b-v2-q8_0", + "7b-v2-fp16", + "7b-v2.1", + "7b-v2.1-q2_K", + "7b-v2.1-q3_K_S", + "7b-v2.1-q3_K_M", + "7b-v2.1-q3_K_L", + "7b-v2.1-q4_0", + "7b-v2.1-q4_1", + "7b-v2.1-q4_K_S", + "7b-v2.1-q4_K_M", + "7b-v2.1-q5_0", + "7b-v2.1-q5_1", + "7b-v2.1-q5_K_S", + "7b-v2.1-q5_K_M", + "7b-v2.1-q6_K", + "7b-v2.1-q8_0", + "7b-v2.1-fp16", + "7b-v2.2", + "7b-v2.2-q2_K", + "7b-v2.2-q3_K_S", + "7b-v2.2-q3_K_M", + "7b-v2.2-q3_K_L", + "7b-v2.2-q4_0", + "7b-v2.2-q4_1", + "7b-v2.2-q4_K_S", + "7b-v2.2-q4_K_M", + "7b-v2.2-q5_0", + "7b-v2.2-q5_1", + "7b-v2.2-q5_K_S", + "7b-v2.2-q5_K_M", + "7b-v2.2-q6_K", + "7b-v2.2-q8_0", + "7b-v2.2-fp16", + "7b-v2.2.1", + "7b-v2.2.1-q2_K", + "7b-v2.2.1-q3_K_S", + "7b-v2.2.1-q3_K_M", + "7b-v2.2.1-q3_K_L", + "7b-v2.2.1-q4_0", + "7b-v2.2.1-q4_1", + "7b-v2.2.1-q4_K_S", + "7b-v2.2.1-q4_K_M", + "7b-v2.2.1-q5_0", + "7b-v2.2.1-q5_1", + "7b-v2.2.1-q5_K_S", + "7b-v2.2.1-q5_K_M", + "7b-v2.2.1-q6_K", + "7b-v2.2.1-q8_0", + "7b-v2.2.1-fp16", + "7b-v2.6", + "7b-v2.6-dpo-laser", + "7b-v2.6-dpo-laser-q2_K", + "7b-v2.6-q2_K", + "7b-v2.6-dpo-laser-q3_K_S", + "7b-v2.6-q3_K_S", + "7b-v2.6-dpo-laser-q3_K_M", + "7b-v2.6-q3_K_M", + "7b-v2.6-dpo-laser-q3_K_L", + "7b-v2.6-q3_K_L", + "7b-v2.6-dpo-laser-q4_0", + "7b-v2.6-q4_0", + "7b-v2.6-dpo-laser-q4_1", + "7b-v2.6-q4_1", + "7b-v2.6-dpo-laser-q4_K_S", + "7b-v2.6-q4_K_S", + "7b-v2.6-dpo-laser-q4_K_M", + "7b-v2.6-q4_K_M", + "7b-v2.6-dpo-laser-q5_0", + "7b-v2.6-q5_0", + "7b-v2.6-dpo-laser-q5_1", + "7b-v2.6-q5_1", + "7b-v2.6-dpo-laser-q5_K_S", + "7b-v2.6-q5_K_S", + "7b-v2.6-dpo-laser-q5_K_M", + "7b-v2.6-q5_K_M", + "7b-v2.6-dpo-laser-q6_K", + "7b-v2.6-q6_K", + "7b-v2.6-dpo-laser-q8_0", + "7b-v2.6-q8_0", + "7b-v2.6-dpo-laser-fp16", + "7b-v2.6-fp16", + "7b-v2.8", + "7b-v2.8-q2_K", + "7b-v2.8-q3_K_S", + "7b-v2.8-q3_K_M", + "7b-v2.8-q3_K_L", + "7b-v2.8-q4_0", + "7b-v2.8-q4_1", + "7b-v2.8-q4_K_S", + "7b-v2.8-q4_K_M", + "7b-v2.8-q5_0", + "7b-v2.8-q5_1", + "7b-v2.8-q5_K_S", + "7b-v2.8-q5_K_M", + "7b-v2.8-q6_K", + "7b-v2.8-q8_0", + "7b-v2.8-fp16" + ], + "capabilities": [] + }, + "wizardlm2": { + "tags": [ + "latest", + "7b", + "8x22b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "8x22b-q2_K", + "8x22b-q4_0", + "8x22b-q8_0", + "8x22b-fp16" + ], + "capabilities": [] + }, + "command-r": { + "tags": [ + "latest", + "v0.1", + "35b", + "35b-08-2024-q2_K", + "35b-08-2024-q3_K_S", + "35b-08-2024-q3_K_M", + "35b-08-2024-q3_K_L", + "35b-08-2024-q4_0", + "35b-08-2024-q4_1", + "35b-08-2024-q4_K_S", + "35b-08-2024-q4_K_M", + "35b-08-2024-q5_0", + "35b-08-2024-q5_1", + "35b-08-2024-q5_K_S", + "35b-08-2024-q5_K_M", + "35b-08-2024-q6_K", + "35b-08-2024-q8_0", + "35b-08-2024-fp16", + "35b-v0.1-q2_K", + "35b-v0.1-q3_K_S", + "35b-v0.1-q3_K_M", + "35b-v0.1-q3_K_L", + "35b-v0.1-q4_0", + "35b-v0.1-q4_1", + "35b-v0.1-q4_K_S", + "35b-v0.1-q4_K_M", + "35b-v0.1-q5_1", + "35b-v0.1-q5_K_S", + "35b-v0.1-q5_K_M", + "35b-v0.1-q6_K", + "35b-v0.1-q8_0", + "35b-v0.1-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "deepcoder": { + "tags": [ + "latest", + "1.5b", + "14b", + "1.5b-preview-q4_K_M", + "1.5b-preview-q8_0", + "1.5b-preview-fp16", + "14b-preview-q4_K_M", + "14b-preview-q8_0", + "14b-preview-fp16" + ], + "capabilities": [] + }, + "granite-code": { + "tags": [ + "latest", + "3b", + "8b", + "20b", + "34b", + "3b-base", + "3b-base-q2_K", + "3b-base-q3_K_S", + "3b-base-q3_K_M", + "3b-base-q3_K_L", + "3b-base-q4_0", + "3b-base-q4_1", + "3b-base-q4_K_S", + "3b-base-q4_K_M", + "3b-base-q5_0", + "3b-base-q5_1", + "3b-base-q5_K_S", + "3b-base-q5_K_M", + "3b-base-q6_K", + "3b-base-q8_0", + "3b-base-fp16", + "3b-instruct", + "3b-instruct-128k-q2_K", + "3b-instruct-q2_K", + "3b-instruct-128k-q3_K_S", + "3b-instruct-q3_K_S", + "3b-instruct-128k-q3_K_M", + "3b-instruct-q3_K_M", + "3b-instruct-128k-q3_K_L", + "3b-instruct-q3_K_L", + "3b-instruct-128k-q4_0", + "3b-instruct-q4_0", + "3b-instruct-128k-q4_1", + "3b-instruct-q4_1", + "3b-instruct-128k-q4_K_S", + "3b-instruct-q4_K_S", + "3b-instruct-128k-q4_K_M", + "3b-instruct-q4_K_M", + "3b-instruct-128k-q5_0", + "3b-instruct-q5_0", + "3b-instruct-128k-q5_1", + "3b-instruct-q5_1", + "3b-instruct-128k-q5_K_S", + "3b-instruct-q5_K_S", + "3b-instruct-128k-q5_K_M", + "3b-instruct-q5_K_M", + "3b-instruct-128k-q6_K", + "3b-instruct-q6_K", + "3b-instruct-128k-q8_0", + "3b-instruct-q8_0", + "3b-instruct-128k-fp16", + "3b-instruct-fp16", + "8b-base", + "8b-base-q2_K", + "8b-base-q3_K_S", + "8b-base-q3_K_M", + "8b-base-q3_K_L", + "8b-base-q4_0", + "8b-base-q4_1", + "8b-base-q4_K_S", + "8b-base-q4_K_M", + "8b-base-q5_0", + "8b-base-q5_1", + "8b-base-q5_K_S", + "8b-base-q5_K_M", + "8b-base-q6_K", + "8b-base-q8_0", + "8b-base-fp16", + "8b-instruct", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-128k-q4_0", + "8b-instruct-q4_0", + "8b-instruct-128k-q4_1", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16", + "20b-base", + "20b-base-q2_K", + "20b-base-q3_K_S", + "20b-base-q3_K_M", + "20b-base-q3_K_L", + "20b-base-q4_0", + "20b-base-q4_1", + "20b-base-q4_K_S", + "20b-base-q4_K_M", + "20b-base-q5_0", + "20b-base-q5_1", + "20b-base-q5_K_S", + "20b-base-q5_K_M", + "20b-base-q6_K", + "20b-base-q8_0", + "20b-base-fp16", + "20b-instruct", + "20b-instruct-8k-q2_K", + "20b-instruct-q2_K", + "20b-instruct-8k-q3_K_S", + "20b-instruct-q3_K_S", + "20b-instruct-8k-q3_K_M", + "20b-instruct-q3_K_M", + "20b-instruct-8k-q3_K_L", + "20b-instruct-q3_K_L", + "20b-instruct-8k-q4_0", + "20b-instruct-q4_0", + "20b-instruct-8k-q4_1", + "20b-instruct-q4_1", + "20b-instruct-8k-q4_K_S", + "20b-instruct-q4_K_S", + "20b-instruct-8k-q4_K_M", + "20b-instruct-q4_K_M", + "20b-instruct-8k-q5_0", + "20b-instruct-q5_0", + "20b-instruct-8k-q5_1", + "20b-instruct-q5_1", + "20b-instruct-8k-q5_K_S", + "20b-instruct-q5_K_S", + "20b-instruct-8k-q5_K_M", + "20b-instruct-q5_K_M", + "20b-instruct-8k-q6_K", + "20b-instruct-q6_K", + "20b-instruct-8k-q8_0", + "20b-instruct-q8_0", + "20b-instruct-8k-fp16", + "34b-base", + "34b-base-q2_K", + "34b-base-q3_K_S", + "34b-base-q3_K_M", + "34b-base-q3_K_L", + "34b-base-q4_0", + "34b-base-q4_1", + "34b-base-q4_K_S", + "34b-base-q4_K_M", + "34b-base-q5_0", + "34b-base-q5_1", + "34b-base-q5_K_S", + "34b-base-q5_K_M", + "34b-base-q6_K", + "34b-base-q8_0", + "34b-instruct", + "34b-instruct-q2_K", + "34b-instruct-q3_K_S", + "34b-instruct-q3_K_M", + "34b-instruct-q3_K_L", + "34b-instruct-q4_0", + "34b-instruct-q4_1", + "34b-instruct-q4_K_S", + "34b-instruct-q4_K_M", + "34b-instruct-q5_0", + "34b-instruct-q5_1", + "34b-instruct-q5_K_S", + "34b-instruct-q5_K_M", + "34b-instruct-q6_K", + "34b-instruct-q8_0" + ], + "capabilities": [] + }, + "moondream": { + "tags": [ + "latest", + "v2", + "1.8b", + "1.8b-v2-q2_K", + "1.8b-v2-q3_K_S", + "1.8b-v2-q3_K_M", + "1.8b-v2-q3_K_L", + "1.8b-v2-q4_0", + "1.8b-v2-q4_1", + "1.8b-v2-q4_K_S", + "1.8b-v2-q4_K_M", + "1.8b-v2-q5_0", + "1.8b-v2-q5_1", + "1.8b-v2-q5_K_S", + "1.8b-v2-q5_K_M", + "1.8b-v2-q6_K", + "1.8b-v2-q8_0", + "1.8b-v2-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "mistral-small3.1": { + "tags": [ + "latest", + "24b", + "24b-instruct-2503-q4_K_M", + "24b-instruct-2503-q8_0", + "24b-instruct-2503-fp16" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "granite4": { + "tags": [ + "latest", + "micro", + "350m", + "1b", + "3b", + "350m-h", + "350m-h-q8_0", + "350m-bf16", + "1b-h", + "1b-h-q8_0", + "1b-bf16", + "3b-h", + "7b-a1b-h", + "32b-a9b-h", + "micro-h", + "small-h", + "tiny-h" + ], + "capabilities": [ + "tools" + ] + }, + "hermes3": { + "tags": [ + "latest", + "3b", + "8b", + "70b", + "405b", + "3b-llama3.2-q2_K", + "3b-llama3.2-q3_K_S", + "3b-llama3.2-q3_K_M", + "3b-llama3.2-q3_K_L", + "3b-llama3.2-q4_0", + "3b-llama3.2-q4_1", + "3b-llama3.2-q4_K_S", + "3b-llama3.2-q4_K_M", + "3b-llama3.2-q5_0", + "3b-llama3.2-q5_1", + "3b-llama3.2-q5_K_S", + "3b-llama3.2-q5_K_M", + "3b-llama3.2-q6_K", + "3b-llama3.2-q8_0", + "3b-llama3.2-fp16", + "8b-llama3.1-q2_K", + "8b-llama3.1-q3_K_S", + "8b-llama3.1-q3_K_M", + "8b-llama3.1-q3_K_L", + "8b-llama3.1-q4_0", + "8b-llama3.1-q4_1", + "8b-llama3.1-q4_K_S", + "8b-llama3.1-q4_K_M", + "8b-llama3.1-q5_0", + "8b-llama3.1-q5_1", + "8b-llama3.1-q5_K_S", + "8b-llama3.1-q5_K_M", + "8b-llama3.1-q6_K", + "8b-llama3.1-q8_0", + "8b-llama3.1-fp16", + "70b-llama3.1-q2_K", + "70b-llama3.1-q3_K_S", + "70b-llama3.1-q3_K_M", + "70b-llama3.1-q3_K_L", + "70b-llama3.1-q4_0", + "70b-llama3.1-q4_1", + "70b-llama3.1-q4_K_S", + "70b-llama3.1-q4_K_M", + "70b-llama3.1-q5_0", + "70b-llama3.1-q5_1", + "70b-llama3.1-q5_K_S", + "70b-llama3.1-q5_K_M", + "70b-llama3.1-q6_K", + "70b-llama3.1-q8_0", + "70b-llama3.1-fp16", + "405b-llama3.1-q2_K", + "405b-llama3.1-q3_K_S", + "405b-llama3.1-q3_K_M", + "405b-llama3.1-q3_K_L", + "405b-llama3.1-q4_0", + "405b-llama3.1-q4_1", + "405b-llama3.1-q4_K_S", + "405b-llama3.1-q4_K_M", + "405b-llama3.1-q5_0", + "405b-llama3.1-q5_1", + "405b-llama3.1-q5_K_S", + "405b-llama3.1-q5_K_M", + "405b-llama3.1-q6_K", + "405b-llama3.1-q8_0", + "405b-llama3.1-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "phi3.5": { + "tags": [ + "latest", + "3.8b", + "3.8b-mini-instruct-q2_K", + "3.8b-mini-instruct-q3_K_S", + "3.8b-mini-instruct-q3_K_M", + "3.8b-mini-instruct-q3_K_L", + "3.8b-mini-instruct-q4_0", + "3.8b-mini-instruct-q4_1", + "3.8b-mini-instruct-q4_K_S", + "3.8b-mini-instruct-q4_K_M", + "3.8b-mini-instruct-q5_0", + "3.8b-mini-instruct-q5_1", + "3.8b-mini-instruct-q5_K_S", + "3.8b-mini-instruct-q5_K_M", + "3.8b-mini-instruct-q6_K", + "3.8b-mini-instruct-q8_0", + "3.8b-mini-instruct-fp16" + ], + "capabilities": [] + }, + "yi": { + "tags": [ + "latest", + "v1.5", + "6b", + "9b", + "34b", + "6b-200k", + "6b-200k-q2_K", + "6b-200k-q3_K_S", + "6b-200k-q3_K_M", + "6b-200k-q3_K_L", + "6b-200k-q4_0", + "6b-200k-q4_1", + "6b-200k-q4_K_S", + "6b-200k-q4_K_M", + "6b-200k-q5_0", + "6b-200k-q5_1", + "6b-200k-q5_K_S", + "6b-200k-q5_K_M", + "6b-200k-q6_K", + "6b-200k-q8_0", + "6b-200k-fp16", + "6b-chat", + "6b-chat-q2_K", + "6b-chat-v1.5-q2_K", + "6b-chat-q3_K_S", + "6b-chat-v1.5-q3_K_S", + "6b-chat-q3_K_M", + "6b-chat-v1.5-q3_K_M", + "6b-chat-q3_K_L", + "6b-chat-v1.5-q3_K_L", + "6b-chat-q4_0", + "6b-chat-v1.5-q4_0", + "6b-chat-q4_1", + "6b-chat-v1.5-q4_1", + "6b-chat-q4_K_S", + "6b-chat-v1.5-q4_K_S", + "6b-chat-q4_K_M", + "6b-chat-v1.5-q4_K_M", + "6b-chat-q5_0", + "6b-chat-v1.5-q5_0", + "6b-chat-q5_1", + "6b-chat-v1.5-q5_1", + "6b-chat-q5_K_S", + "6b-chat-v1.5-q5_K_S", + "6b-chat-q5_K_M", + "6b-chat-v1.5-q5_K_M", + "6b-chat-q6_K", + "6b-chat-v1.5-q6_K", + "6b-chat-q8_0", + "6b-chat-v1.5-q8_0", + "6b-chat-fp16", + "6b-chat-v1.5-fp16", + "6b-v1.5", + "6b-v1.5-q2_K", + "6b-v1.5-q3_K_S", + "6b-v1.5-q3_K_M", + "6b-v1.5-q3_K_L", + "6b-v1.5-q4_0", + "6b-v1.5-q4_1", + "6b-v1.5-q4_K_S", + "6b-v1.5-q4_K_M", + "6b-v1.5-q5_0", + "6b-v1.5-q5_1", + "6b-v1.5-q5_K_S", + "6b-v1.5-q5_K_M", + "6b-v1.5-q6_K", + "6b-v1.5-q8_0", + "6b-v1.5-fp16", + "6b-q2_K", + "6b-q3_K_S", + "6b-q3_K_M", + "6b-q3_K_L", + "6b-q4_0", + "6b-q4_1", + "6b-q4_K_S", + "6b-q4_K_M", + "6b-q5_0", + "6b-q5_1", + "6b-q5_K_S", + "6b-q5_K_M", + "6b-q6_K", + "6b-q8_0", + "6b-fp16", + "9b-chat", + "9b-chat-v1.5-q2_K", + "9b-chat-v1.5-q3_K_S", + "9b-chat-v1.5-q3_K_M", + "9b-chat-v1.5-q3_K_L", + "9b-chat-v1.5-q4_0", + "9b-chat-v1.5-q4_1", + "9b-chat-v1.5-q4_K_S", + "9b-chat-v1.5-q4_K_M", + "9b-chat-v1.5-q5_0", + "9b-chat-v1.5-q5_1", + "9b-chat-v1.5-q5_K_S", + "9b-chat-v1.5-q5_K_M", + "9b-chat-v1.5-q6_K", + "9b-chat-v1.5-q8_0", + "9b-chat-v1.5-fp16", + "9b-v1.5", + "9b-v1.5-q2_K", + "9b-v1.5-q3_K_S", + "9b-v1.5-q3_K_M", + "9b-v1.5-q3_K_L", + "9b-v1.5-q4_0", + "9b-v1.5-q4_1", + "9b-v1.5-q4_K_S", + "9b-v1.5-q4_K_M", + "9b-v1.5-q5_0", + "9b-v1.5-q5_1", + "9b-v1.5-q5_K_S", + "9b-v1.5-q5_K_M", + "9b-v1.5-q6_K", + "9b-v1.5-q8_0", + "9b-v1.5-fp16", + "34b-chat", + "34b-chat-q2_K", + "34b-chat-v1.5-q2_K", + "34b-chat-q3_K_S", + "34b-chat-v1.5-q3_K_S", + "34b-chat-q3_K_M", + "34b-chat-v1.5-q3_K_M", + "34b-chat-q3_K_L", + "34b-chat-v1.5-q3_K_L", + "34b-chat-q4_0", + "34b-chat-v1.5-q4_0", + "34b-chat-q4_1", + "34b-chat-v1.5-q4_1", + "34b-chat-q4_K_S", + "34b-chat-v1.5-q4_K_S", + "34b-chat-q4_K_M", + "34b-chat-v1.5-q4_K_M", + "34b-chat-q5_0", + "34b-chat-v1.5-q5_0", + "34b-chat-q5_1", + "34b-chat-v1.5-q5_1", + "34b-chat-q5_K_S", + "34b-chat-v1.5-q5_K_S", + "34b-chat-q5_K_M", + "34b-chat-v1.5-q5_K_M", + "34b-chat-q6_K", + "34b-chat-v1.5-q6_K", + "34b-chat-q8_0", + "34b-chat-v1.5-q8_0", + "34b-chat-fp16", + "34b-chat-v1.5-fp16", + "34b-v1.5", + "34b-v1.5-q2_K", + "34b-v1.5-q3_K_S", + "34b-v1.5-q3_K_M", + "34b-v1.5-q3_K_L", + "34b-v1.5-q4_0", + "34b-v1.5-q4_1", + "34b-v1.5-q4_K_S", + "34b-v1.5-q4_K_M", + "34b-v1.5-q5_0", + "34b-v1.5-q5_1", + "34b-v1.5-q5_K_S", + "34b-v1.5-q5_K_M", + "34b-v1.5-q6_K", + "34b-v1.5-q8_0", + "34b-v1.5-fp16", + "34b-q2_K", + "34b-q3_K_S", + "34b-q3_K_M", + "34b-q3_K_L", + "34b-q4_0", + "34b-q4_1", + "34b-q4_K_S", + "34b-q4_K_M", + "34b-q5_0", + "34b-q5_1", + "34b-q5_K_S", + "34b-q6_K" + ], + "capabilities": [] + }, + "bakllava": { + "tags": [ + "latest", + "7b", + "7b-v1-q2_K", + "7b-v1-q3_K_S", + "7b-v1-q3_K_M", + "7b-v1-q3_K_L", + "7b-v1-q4_0", + "7b-v1-q4_1", + "7b-v1-q4_K_S", + "7b-v1-q4_K_M", + "7b-v1-q5_0", + "7b-v1-q5_1", + "7b-v1-q5_K_S", + "7b-v1-q5_K_M", + "7b-v1-q6_K", + "7b-v1-q8_0", + "7b-v1-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "zephyr": { + "tags": [ + "latest", + "7b", + "141b", + "7b-alpha", + "7b-alpha-q2_K", + "7b-alpha-q3_K_S", + "7b-alpha-q3_K_M", + "7b-alpha-q3_K_L", + "7b-alpha-q4_0", + "7b-alpha-q4_1", + "7b-alpha-q4_K_S", + "7b-alpha-q4_K_M", + "7b-alpha-q5_0", + "7b-alpha-q5_1", + "7b-alpha-q5_K_S", + "7b-alpha-q5_K_M", + "7b-alpha-q6_K", + "7b-alpha-q8_0", + "7b-alpha-fp16", + "7b-beta", + "7b-beta-q2_K", + "7b-beta-q3_K_S", + "7b-beta-q3_K_M", + "7b-beta-q3_K_L", + "7b-beta-q4_0", + "7b-beta-q4_1", + "7b-beta-q4_K_S", + "7b-beta-q4_K_M", + "7b-beta-q5_0", + "7b-beta-q5_1", + "7b-beta-q5_K_S", + "7b-beta-q5_K_M", + "7b-beta-q6_K", + "7b-beta-q8_0", + "7b-beta-fp16", + "141b-v0.1", + "141b-v0.1-q2_K", + "141b-v0.1-q4_0", + "141b-v0.1-q8_0", + "141b-v0.1-fp16" + ], + "capabilities": [] + }, + "mistral-large": { + "tags": [ + "latest", + "123b", + "123b-instruct-2407-q2_K", + "123b-instruct-2407-q3_K_S", + "123b-instruct-2407-q3_K_M", + "123b-instruct-2407-q3_K_L", + "123b-instruct-2407-q4_0", + "123b-instruct-2407-q4_1", + "123b-instruct-2407-q4_K_S", + "123b-instruct-2407-q4_K_M", + "123b-instruct-2407-q5_0", + "123b-instruct-2407-q5_1", + "123b-instruct-2407-q5_K_S", + "123b-instruct-2407-q5_K_M", + "123b-instruct-2407-q6_K", + "123b-instruct-2407-q8_0", + "123b-instruct-2407-fp16", + "123b-instruct-2411-q2_K", + "123b-instruct-2411-q3_K_S", + "123b-instruct-2411-q3_K_M", + "123b-instruct-2411-q3_K_L", + "123b-instruct-2411-q4_0", + "123b-instruct-2411-q4_1", + "123b-instruct-2411-q4_K_S", + "123b-instruct-2411-q4_K_M", + "123b-instruct-2411-q5_0", + "123b-instruct-2411-q5_1", + "123b-instruct-2411-q5_K_S", + "123b-instruct-2411-q5_K_M", + "123b-instruct-2411-q6_K", + "123b-instruct-2411-q8_0", + "123b-instruct-2411-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "wizard-vicuna-uncensored": { + "tags": [ + "latest", + "7b", + "13b", + "30b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "30b-q2_K", + "30b-q3_K_S", + "30b-q3_K_M", + "30b-q3_K_L", + "30b-q4_0", + "30b-q4_1", + "30b-q4_K_S", + "30b-q4_K_M", + "30b-q5_0", + "30b-q5_1", + "30b-q5_K_S", + "30b-q5_K_M", + "30b-q6_K", + "30b-q8_0", + "30b-fp16" + ], + "capabilities": [] + }, + "exaone-deep": { + "tags": [ + "latest", + "2.4b", + "7.8b", + "32b", + "2.4b-q4_K_M", + "2.4b-q8_0", + "2.4b-fp16", + "7.8b-q4_K_M", + "7.8b-q8_0", + "7.8b-fp16", + "32b-q4_K_M", + "32b-q8_0", + "32b-fp16" + ], + "capabilities": [] + }, + "embeddinggemma": { + "tags": [ + "latest", + "300m", + "300m-qat-q4_0", + "300m-qat-q8_0", + "300m-bf16" + ], + "capabilities": [ + "embedding" + ] + }, + "starcoder": { + "tags": [ + "latest", + "1b", + "3b", + "7b", + "15b", + "1b-base", + "1b-base-q2_K", + "1b-base-q3_K_S", + "1b-base-q3_K_M", + "1b-base-q3_K_L", + "1b-base-q4_0", + "1b-base-q4_1", + "1b-base-q4_K_S", + "1b-base-q4_K_M", + "1b-base-q5_0", + "1b-base-q5_1", + "1b-base-q5_K_S", + "1b-base-q5_K_M", + "1b-base-q6_K", + "1b-base-q8_0", + "1b-base-fp16", + "3b-base", + "3b-base-q2_K", + "3b-base-q3_K_S", + "3b-base-q3_K_M", + "3b-base-q3_K_L", + "3b-base-q4_0", + "3b-base-q4_1", + "3b-base-q4_K_S", + "3b-base-q4_K_M", + "3b-base-q5_0", + "3b-base-q5_1", + "3b-base-q5_K_S", + "3b-base-q5_K_M", + "3b-base-q6_K", + "3b-base-q8_0", + "3b-base-fp16", + "7b-base", + "7b-base-q2_K", + "7b-base-q3_K_S", + "7b-base-q3_K_M", + "7b-base-q3_K_L", + "7b-base-q4_0", + "7b-base-q4_1", + "7b-base-q4_K_S", + "7b-base-q4_K_M", + "7b-base-q5_0", + "7b-base-q5_1", + "7b-base-q5_K_S", + "7b-base-q5_K_M", + "7b-base-q6_K", + "7b-base-q8_0", + "7b-base-fp16", + "15b-base", + "15b-base-q2_K", + "15b-base-q3_K_S", + "15b-base-q3_K_M", + "15b-base-q3_K_L", + "15b-base-q4_0", + "15b-base-q4_1", + "15b-base-q4_K_S", + "15b-base-q4_K_M", + "15b-base-q5_0", + "15b-base-q5_1", + "15b-base-q5_K_S", + "15b-base-q5_K_M", + "15b-base-q6_K", + "15b-base-q8_0", + "15b-base-fp16", + "15b-plus", + "15b-plus-q2_K", + "15b-plus-q3_K_S", + "15b-plus-q3_K_M", + "15b-plus-q3_K_L", + "15b-plus-q4_0", + "15b-plus-q4_1", + "15b-plus-q4_K_S", + "15b-plus-q4_K_M", + "15b-plus-q5_0", + "15b-plus-q5_1", + "15b-plus-q5_K_S", + "15b-plus-q5_K_M", + "15b-plus-q6_K", + "15b-plus-q8_0", + "15b-plus-fp16", + "15b-q2_K", + "15b-q3_K_S", + "15b-q3_K_M", + "15b-q3_K_L", + "15b-q4_0", + "15b-q4_1", + "15b-q4_K_S", + "15b-q4_K_M", + "15b-q5_0", + "15b-q5_1", + "15b-q5_K_S", + "15b-q5_K_M", + "15b-q6_K", + "15b-q8_0", + "15b-fp16" + ], + "capabilities": [] + }, + "nous-hermes": { + "tags": [ + "latest", + "7b", + "13b", + "7b-llama2", + "7b-llama2-q2_K", + "7b-llama2-q3_K_S", + "7b-llama2-q3_K_M", + "7b-llama2-q3_K_L", + "7b-llama2-q4_0", + "7b-llama2-q4_1", + "7b-llama2-q4_K_S", + "7b-llama2-q4_K_M", + "7b-llama2-q5_0", + "7b-llama2-q5_1", + "7b-llama2-q5_K_S", + "7b-llama2-q5_K_M", + "7b-llama2-q6_K", + "7b-llama2-q8_0", + "7b-llama2-fp16", + "13b-llama2", + "13b-llama2-q2_K", + "13b-llama2-q3_K_S", + "13b-llama2-q3_K_M", + "13b-llama2-q3_K_L", + "13b-llama2-q4_0", + "13b-llama2-q4_1", + "13b-llama2-q4_K_S", + "13b-llama2-q4_K_M", + "13b-llama2-q5_0", + "13b-llama2-q5_1", + "13b-llama2-q5_K_S", + "13b-llama2-q5_K_M", + "13b-llama2-q6_K", + "13b-llama2-q8_0", + "13b-llama2-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "70b-llama2-q2_K", + "70b-llama2-q3_K_S", + "70b-llama2-q3_K_M", + "70b-llama2-q3_K_L", + "70b-llama2-q4_0", + "70b-llama2-q4_1", + "70b-llama2-q4_K_S", + "70b-llama2-q4_K_M", + "70b-llama2-q5_0", + "70b-llama2-q5_1", + "70b-llama2-q5_K_M", + "70b-llama2-q6_K", + "70b-llama2-fp16" + ], + "capabilities": [] + }, + "deepseek-llm": { + "tags": [ + "latest", + "7b", + "67b", + "7b-base", + "7b-base-q2_K", + "7b-base-q3_K_S", + "7b-base-q3_K_M", + "7b-base-q3_K_L", + "7b-base-q4_0", + "7b-base-q4_1", + "7b-base-q4_K_S", + "7b-base-q4_K_M", + "7b-base-q5_0", + "7b-base-q5_1", + "7b-base-q5_K_S", + "7b-base-q5_K_M", + "7b-base-q6_K", + "7b-base-q8_0", + "7b-base-fp16", + "7b-chat", + "7b-chat-q2_K", + "7b-chat-q3_K_S", + "7b-chat-q3_K_M", + "7b-chat-q3_K_L", + "7b-chat-q4_0", + "7b-chat-q4_1", + "7b-chat-q4_K_S", + "7b-chat-q4_K_M", + "7b-chat-q5_0", + "7b-chat-q5_1", + "7b-chat-q5_K_S", + "7b-chat-q5_K_M", + "7b-chat-q6_K", + "7b-chat-q8_0", + "7b-chat-fp16", + "67b-base", + "67b-base-q2_K", + "67b-base-q3_K_S", + "67b-base-q3_K_M", + "67b-base-q3_K_L", + "67b-base-q4_0", + "67b-base-q4_1", + "67b-base-q4_K_S", + "67b-base-q4_K_M", + "67b-base-q5_0", + "67b-base-q5_1", + "67b-base-q5_K_S", + "67b-base-q5_K_M", + "67b-base-q6_K", + "67b-base-q8_0", + "67b-base-fp16", + "67b-chat", + "67b-chat-q2_K", + "67b-chat-q3_K_S", + "67b-chat-q3_K_M", + "67b-chat-q3_K_L", + "67b-chat-q4_0", + "67b-chat-q4_1", + "67b-chat-q4_K_S", + "67b-chat-q4_K_M", + "67b-chat-q5_0", + "67b-chat-q5_1", + "67b-chat-q5_K_S", + "67b-chat-fp16" + ], + "capabilities": [] + }, + "falcon": { + "tags": [ + "latest", + "instruct", + "text", + "7b", + "40b", + "180b", + "7b-instruct", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "7b-text", + "7b-text-q4_0", + "7b-text-q4_1", + "7b-text-q5_0", + "7b-text-q5_1", + "7b-text-q8_0", + "7b-text-fp16", + "40b-instruct", + "40b-instruct-q4_0", + "40b-instruct-q4_1", + "40b-instruct-q5_0", + "40b-instruct-q5_1", + "40b-instruct-q8_0", + "40b-instruct-fp16", + "40b-text", + "40b-text-q4_0", + "40b-text-q4_1", + "40b-text-q5_0", + "40b-text-q5_1", + "40b-text-q8_0", + "40b-text-fp16", + "180b-chat", + "180b-chat-q4_0", + "180b-text", + "180b-text-q4_0" + ], + "capabilities": [] + }, + "opencoder": { + "tags": [ + "latest", + "1.5b", + "8b", + "1.5b-instruct-q4_K_M", + "1.5b-instruct-q8_0", + "1.5b-instruct-fp16", + "8b-instruct-q4_K_M", + "8b-instruct-q8_0", + "8b-instruct-fp16" + ], + "capabilities": [] + }, + "openchat": { + "tags": [ + "latest", + "7b", + "7b-v3.5", + "7b-v3.5-0106", + "7b-v3.5-0106-q2_K", + "7b-v3.5-q2_K", + "7b-v3.5-0106-q3_K_S", + "7b-v3.5-q3_K_S", + "7b-v3.5-0106-q3_K_M", + "7b-v3.5-q3_K_M", + "7b-v3.5-0106-q3_K_L", + "7b-v3.5-q3_K_L", + "7b-v3.5-0106-q4_0", + "7b-v3.5-q4_0", + "7b-v3.5-0106-q4_1", + "7b-v3.5-q4_1", + "7b-v3.5-0106-q4_K_S", + "7b-v3.5-q4_K_S", + "7b-v3.5-0106-q4_K_M", + "7b-v3.5-q4_K_M", + "7b-v3.5-0106-q5_0", + "7b-v3.5-q5_0", + "7b-v3.5-0106-q5_1", + "7b-v3.5-q5_1", + "7b-v3.5-0106-q5_K_S", + "7b-v3.5-0106-q5_K_M", + "7b-v3.5-0106-q6_K", + "7b-v3.5-0106-q8_0", + "7b-v3.5-0106-fp16", + "7b-v3.5-1210", + "7b-v3.5-1210-q2_K", + "7b-v3.5-1210-q3_K_S", + "7b-v3.5-1210-q3_K_M", + "7b-v3.5-1210-q3_K_L", + "7b-v3.5-1210-q4_0", + "7b-v3.5-1210-q4_1", + "7b-v3.5-1210-q4_K_S", + "7b-v3.5-1210-q4_K_M", + "7b-v3.5-1210-q5_0", + "7b-v3.5-1210-q5_1", + "7b-v3.5-1210-q5_K_S", + "7b-v3.5-q5_K_S", + "7b-v3.5-1210-q5_K_M", + "7b-v3.5-q5_K_M", + "7b-v3.5-1210-q6_K", + "7b-v3.5-q6_K", + "7b-v3.5-1210-q8_0", + "7b-v3.5-q8_0", + "7b-v3.5-1210-fp16", + "7b-v3.5-fp16" + ], + "capabilities": [] + }, + "vicuna": { + "tags": [ + "latest", + "7b", + "13b", + "33b", + "7b-16k", + "7b-v1.5-16k-q2_K", + "7b-v1.5-q2_K", + "7b-v1.5-16k-q3_K_S", + "7b-v1.5-q3_K_S", + "7b-v1.5-16k-q3_K_M", + "7b-v1.5-q3_K_M", + "7b-v1.5-16k-q3_K_L", + "7b-v1.5-q3_K_L", + "7b-v1.5-16k-q4_0", + "7b-v1.5-q4_0", + "7b-v1.5-16k-q4_1", + "7b-v1.5-q4_1", + "7b-v1.5-16k-q4_K_S", + "7b-v1.5-q4_K_S", + "7b-v1.5-16k-q4_K_M", + "7b-v1.5-q4_K_M", + "7b-v1.5-16k-q5_0", + "7b-v1.5-q5_0", + "7b-v1.5-16k-q5_1", + "7b-v1.5-q5_1", + "7b-v1.5-16k-q5_K_S", + "7b-v1.5-q5_K_S", + "7b-v1.5-16k-q5_K_M", + "7b-v1.5-q5_K_M", + "7b-v1.5-16k-q6_K", + "7b-v1.5-q6_K", + "7b-v1.5-16k-q8_0", + "7b-v1.5-q8_0", + "7b-v1.5-16k-fp16", + "7b-v1.5-fp16", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-16k", + "13b-v1.5-16k-q2_K", + "13b-v1.5-q2_K", + "13b-v1.5-16k-q3_K_S", + "13b-v1.5-q3_K_S", + "13b-v1.5-16k-q3_K_M", + "13b-v1.5-q3_K_M", + "13b-v1.5-16k-q3_K_L", + "13b-v1.5-q3_K_L", + "13b-v1.5-16k-q4_0", + "13b-v1.5-q4_0", + "13b-v1.5-16k-q4_1", + "13b-v1.5-q4_1", + "13b-v1.5-16k-q4_K_S", + "13b-v1.5-q4_K_S", + "13b-v1.5-16k-q4_K_M", + "13b-v1.5-q4_K_M", + "13b-v1.5-16k-q5_0", + "13b-v1.5-q5_0", + "13b-v1.5-16k-q5_1", + "13b-v1.5-q5_1", + "13b-v1.5-16k-q5_K_S", + "13b-v1.5-q5_K_S", + "13b-v1.5-16k-q5_K_M", + "13b-v1.5-q5_K_M", + "13b-v1.5-16k-q6_K", + "13b-v1.5-q6_K", + "13b-v1.5-16k-q8_0", + "13b-v1.5-q8_0", + "13b-v1.5-16k-fp16", + "13b-v1.5-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "33b-q2_K", + "33b-q3_K_S", + "33b-q3_K_M", + "33b-q3_K_L", + "33b-q4_0", + "33b-q4_1", + "33b-q4_K_S", + "33b-q4_K_M", + "33b-q5_0", + "33b-q5_1", + "33b-q5_K_S", + "33b-q5_K_M", + "33b-q6_K", + "33b-q8_0", + "33b-fp16" + ], + "capabilities": [] + }, + "deepseek-v2": { + "tags": [ + "latest", + "lite", + "16b", + "236b", + "16b-lite-chat-q2_K", + "16b-lite-chat-q3_K_S", + "16b-lite-chat-q3_K_M", + "16b-lite-chat-q3_K_L", + "16b-lite-chat-q4_0", + "16b-lite-chat-q4_1", + "16b-lite-chat-q4_K_S", + "16b-lite-chat-q4_K_M", + "16b-lite-chat-q5_0", + "16b-lite-chat-q5_1", + "16b-lite-chat-q5_K_S", + "16b-lite-chat-q5_K_M", + "16b-lite-chat-q6_K", + "16b-lite-chat-q8_0", + "16b-lite-chat-fp16", + "236b-chat-q2_K", + "236b-chat-q3_K_S", + "236b-chat-q3_K_M", + "236b-chat-q3_K_L", + "236b-chat-q4_0", + "236b-chat-q4_1", + "236b-chat-q4_K_S", + "236b-chat-q4_K_M", + "236b-chat-q5_0", + "236b-chat-q5_1", + "236b-chat-q5_K_S", + "236b-chat-q5_K_M", + "236b-chat-q6_K", + "236b-chat-q8_0", + "236b-chat-fp16" + ], + "capabilities": [] + }, + "openhermes": { + "tags": [ + "latest", + "v2", + "v2.5", + "7b-mistral-v2-q2_K", + "7b-mistral-v2-q3_K_S", + "7b-mistral-v2-q3_K_M", + "7b-mistral-v2-q3_K_L", + "7b-mistral-v2-q4_0", + "7b-mistral-v2-q4_1", + "7b-mistral-v2-q4_K_S", + "7b-mistral-v2-q4_K_M", + "7b-mistral-v2-q5_0", + "7b-mistral-v2-q5_1", + "7b-mistral-v2-q5_K_S", + "7b-mistral-v2-q5_K_M", + "7b-mistral-v2-q6_K", + "7b-mistral-v2-q8_0", + "7b-mistral-v2-fp16", + "7b-mistral-v2.5-q2_K", + "7b-mistral-v2.5-q3_K_S", + "7b-mistral-v2.5-q3_K_M", + "7b-mistral-v2.5-q3_K_L", + "7b-mistral-v2.5-q4_0", + "7b-mistral-v2.5-q4_1", + "7b-mistral-v2.5-q4_K_S", + "7b-mistral-v2.5-q4_K_M", + "7b-mistral-v2.5-q5_0", + "7b-mistral-v2.5-q5_1", + "7b-mistral-v2.5-q5_K_S", + "7b-mistral-v2.5-q5_K_M", + "7b-mistral-v2.5-q6_K", + "7b-mistral-v2.5-q8_0", + "7b-mistral-v2.5-fp16", + "7b-v2", + "7b-v2.5" + ], + "capabilities": [] + }, + "codeqwen": { + "tags": [ + "latest", + "chat", + "code", + "v1.5", + "7b", + "7b-chat", + "7b-chat-v1.5-q2_K", + "7b-chat-v1.5-q3_K_S", + "7b-chat-v1.5-q3_K_M", + "7b-chat-v1.5-q3_K_L", + "7b-chat-v1.5-q4_0", + "7b-chat-v1.5-q4_1", + "7b-chat-v1.5-q4_K_S", + "7b-chat-v1.5-q4_K_M", + "7b-chat-v1.5-q5_0", + "7b-chat-v1.5-q5_1", + "7b-chat-v1.5-q5_K_S", + "7b-chat-v1.5-q5_K_M", + "7b-chat-v1.5-q6_K", + "7b-chat-v1.5-q8_0", + "7b-chat-v1.5-fp16", + "7b-code", + "7b-code-v1.5-q4_0", + "7b-code-v1.5-q4_1", + "7b-code-v1.5-q5_0", + "7b-code-v1.5-q5_1", + "7b-code-v1.5-q8_0", + "7b-code-v1.5-fp16", + "v1.5-chat", + "v1.5-code" + ], + "capabilities": [] + }, + "paraphrase-multilingual": { + "tags": [ + "latest", + "278m", + "278m-mpnet-base-v2-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "qwen2-math": { + "tags": [ + "latest", + "1.5b", + "7b", + "72b", + "1.5b-instruct", + "1.5b-instruct-q2_K", + "1.5b-instruct-q3_K_S", + "1.5b-instruct-q3_K_M", + "1.5b-instruct-q3_K_L", + "1.5b-instruct-q4_0", + "1.5b-instruct-q4_1", + "1.5b-instruct-q4_K_S", + "1.5b-instruct-q4_K_M", + "1.5b-instruct-q5_0", + "1.5b-instruct-q5_1", + "1.5b-instruct-q5_K_S", + "1.5b-instruct-q5_K_M", + "1.5b-instruct-q6_K", + "1.5b-instruct-q8_0", + "1.5b-instruct-fp16", + "7b-instruct", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "72b-instruct", + "72b-instruct-q2_K", + "72b-instruct-q3_K_S", + "72b-instruct-q3_K_M", + "72b-instruct-q3_K_L", + "72b-instruct-q4_0", + "72b-instruct-q4_1", + "72b-instruct-q4_K_S", + "72b-instruct-q4_K_M", + "72b-instruct-q5_0", + "72b-instruct-q5_1", + "72b-instruct-q5_K_S", + "72b-instruct-q5_K_M", + "72b-instruct-q6_K", + "72b-instruct-q8_0", + "72b-instruct-fp16" + ], + "capabilities": [] + }, + "glm4": { + "tags": [ + "latest", + "9b", + "9b-chat-q2_K", + "9b-chat-q3_K_S", + "9b-chat-q3_K_M", + "9b-chat-q3_K_L", + "9b-chat-q4_0", + "9b-chat-q4_1", + "9b-chat-q4_K_S", + "9b-chat-q4_K_M", + "9b-chat-q5_0", + "9b-chat-q5_1", + "9b-chat-q5_K_S", + "9b-chat-q5_K_M", + "9b-chat-q6_K", + "9b-chat-q8_0", + "9b-chat-fp16", + "9b-text-q2_K", + "9b-text-q3_K_S", + "9b-text-q3_K_M", + "9b-text-q3_K_L", + "9b-text-q4_0", + "9b-text-q4_1", + "9b-text-q4_K_S", + "9b-text-q4_K_M", + "9b-text-q5_0", + "9b-text-q5_1", + "9b-text-q5_K_S", + "9b-text-q5_K_M", + "9b-text-q6_K", + "9b-text-q8_0", + "9b-text-fp16" + ], + "capabilities": [] + }, + "aya": { + "tags": [ + "latest", + "8b", + "35b", + "8b-23", + "8b-23-q2_K", + "8b-23-q3_K_S", + "8b-23-q3_K_M", + "8b-23-q3_K_L", + "8b-23-q4_0", + "8b-23-q4_1", + "8b-23-q4_K_S", + "8b-23-q4_K_M", + "8b-23-q5_0", + "8b-23-q5_1", + "8b-23-q5_K_S", + "8b-23-q5_K_M", + "8b-23-q6_K", + "8b-23-q8_0", + "35b-23", + "35b-23-q2_K", + "35b-23-q3_K_S", + "35b-23-q3_K_M", + "35b-23-q3_K_L", + "35b-23-q4_0", + "35b-23-q4_1", + "35b-23-q4_K_S", + "35b-23-q4_K_M", + "35b-23-q5_0", + "35b-23-q5_1", + "35b-23-q5_K_S", + "35b-23-q5_K_M", + "35b-23-q6_K", + "35b-23-q8_0" + ], + "capabilities": [] + }, + "llama2-chinese": { + "tags": [ + "latest", + "7b", + "13b", + "7b-chat", + "7b-chat-q2_K", + "7b-chat-q3_K_S", + "7b-chat-q3_K_M", + "7b-chat-q3_K_L", + "7b-chat-q4_0", + "7b-chat-q4_1", + "7b-chat-q4_K_S", + "7b-chat-q4_K_M", + "7b-chat-q5_0", + "7b-chat-q5_1", + "7b-chat-q5_K_S", + "7b-chat-q5_K_M", + "7b-chat-q6_K", + "7b-chat-q8_0", + "7b-chat-fp16", + "13b-chat", + "13b-chat-q2_K", + "13b-chat-q3_K_S", + "13b-chat-q3_K_M", + "13b-chat-q3_K_L", + "13b-chat-q4_0", + "13b-chat-q4_1", + "13b-chat-q4_K_S", + "13b-chat-q4_K_M", + "13b-chat-q5_0", + "13b-chat-q5_1", + "13b-chat-q5_K_S", + "13b-chat-q5_K_M", + "13b-chat-q6_K", + "13b-chat-q8_0", + "13b-chat-fp16" + ], + "capabilities": [] + }, + "qwen3-embedding": { + "tags": [ + "latest", + "0.6b", + "4b", + "8b", + "0.6b-q8_0", + "0.6b-fp16", + "4b-q4_K_M", + "4b-q8_0", + "4b-fp16", + "8b-q4_K_M", + "8b-q8_0", + "8b-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "stable-code": { + "tags": [ + "latest", + "code", + "instruct", + "3b", + "3b-code", + "3b-code-q2_K", + "3b-code-q3_K_S", + "3b-code-q3_K_M", + "3b-code-q3_K_L", + "3b-code-q4_0", + "3b-code-q4_1", + "3b-code-q4_K_S", + "3b-code-q4_K_M", + "3b-code-q5_0", + "3b-code-q5_1", + "3b-code-q5_K_S", + "3b-code-q5_K_M", + "3b-code-q6_K", + "3b-code-q8_0", + "3b-code-fp16", + "3b-instruct", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16" + ], + "capabilities": [] + }, + "neural-chat": { + "tags": [ + "latest", + "7b", + "7b-v3.1", + "7b-v3.1-q2_K", + "7b-v3.1-q3_K_S", + "7b-v3.1-q3_K_M", + "7b-v3.1-q3_K_L", + "7b-v3.1-q4_0", + "7b-v3.1-q4_1", + "7b-v3.1-q4_K_S", + "7b-v3.1-q4_K_M", + "7b-v3.1-q5_0", + "7b-v3.1-q5_1", + "7b-v3.1-q5_K_S", + "7b-v3.1-q5_K_M", + "7b-v3.1-q6_K", + "7b-v3.1-q8_0", + "7b-v3.1-fp16", + "7b-v3.2", + "7b-v3.2-q2_K", + "7b-v3.2-q3_K_S", + "7b-v3.2-q3_K_M", + "7b-v3.2-q3_K_L", + "7b-v3.2-q4_0", + "7b-v3.2-q4_1", + "7b-v3.2-q4_K_S", + "7b-v3.2-q4_K_M", + "7b-v3.2-q5_0", + "7b-v3.2-q5_1", + "7b-v3.2-q5_K_S", + "7b-v3.2-q5_K_M", + "7b-v3.2-q6_K", + "7b-v3.2-q8_0", + "7b-v3.2-fp16", + "7b-v3.3", + "7b-v3.3-q2_K", + "7b-v3.3-q3_K_S", + "7b-v3.3-q3_K_M", + "7b-v3.3-q3_K_L", + "7b-v3.3-q4_0", + "7b-v3.3-q4_1", + "7b-v3.3-q4_K_S", + "7b-v3.3-q4_K_M", + "7b-v3.3-q5_0", + "7b-v3.3-q5_1", + "7b-v3.3-q5_K_S", + "7b-v3.3-q5_K_M", + "7b-v3.3-q6_K", + "7b-v3.3-q8_0", + "7b-v3.3-fp16" + ], + "capabilities": [] + }, + "command-r-plus": { + "tags": [ + "latest", + "104b", + "104b-08-2024-q2_K", + "104b-08-2024-q3_K_S", + "104b-08-2024-q3_K_M", + "104b-08-2024-q3_K_L", + "104b-08-2024-q4_0", + "104b-08-2024-q4_1", + "104b-08-2024-q4_K_S", + "104b-08-2024-q4_K_M", + "104b-08-2024-q5_0", + "104b-08-2024-q5_1", + "104b-08-2024-q5_K_S", + "104b-08-2024-q5_K_M", + "104b-08-2024-q6_K", + "104b-08-2024-q8_0", + "104b-08-2024-fp16", + "104b-q2_K", + "104b-q4_0", + "104b-q8_0", + "104b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "nous-hermes2": { + "tags": [ + "latest", + "10.7b", + "34b", + "10.7b-solar-q2_K", + "10.7b-solar-q3_K_S", + "10.7b-solar-q3_K_M", + "10.7b-solar-q3_K_L", + "10.7b-solar-q4_0", + "10.7b-solar-q4_1", + "10.7b-solar-q4_K_S", + "10.7b-solar-q4_K_M", + "10.7b-solar-q5_0", + "10.7b-solar-q5_1", + "10.7b-solar-q5_K_S", + "10.7b-solar-q5_K_M", + "10.7b-solar-q6_K", + "10.7b-solar-q8_0", + "10.7b-solar-fp16", + "34b-yi-q2_K", + "34b-yi-q3_K_S", + "34b-yi-q3_K_M", + "34b-yi-q3_K_L", + "34b-yi-q4_0", + "34b-yi-q4_1", + "34b-yi-q4_K_S", + "34b-yi-q4_K_M", + "34b-yi-q5_0", + "34b-yi-q5_1", + "34b-yi-q5_K_S", + "34b-yi-q5_K_M", + "34b-yi-q6_K", + "34b-yi-q8_0", + "34b-yi-fp16" + ], + "capabilities": [] + }, + "wizardcoder": { + "tags": [ + "latest", + "python", + "33b", + "7b-python", + "7b-python-q2_K", + "7b-python-q3_K_S", + "7b-python-q3_K_M", + "7b-python-q3_K_L", + "7b-python-q4_0", + "7b-python-q4_1", + "7b-python-q4_K_S", + "7b-python-q4_K_M", + "7b-python-q5_0", + "7b-python-q5_1", + "7b-python-q5_K_S", + "7b-python-q5_K_M", + "7b-python-q6_K", + "7b-python-q8_0", + "7b-python-fp16", + "13b-python", + "13b-python-q2_K", + "13b-python-q3_K_S", + "13b-python-q3_K_M", + "13b-python-q3_K_L", + "13b-python-q4_0", + "13b-python-q4_1", + "13b-python-q4_K_S", + "13b-python-q4_K_M", + "13b-python-q5_0", + "13b-python-q5_1", + "13b-python-q5_K_S", + "13b-python-q5_K_M", + "13b-python-q6_K", + "13b-python-q8_0", + "13b-python-fp16", + "33b-v1.1", + "33b-v1.1-q2_K", + "33b-v1.1-q3_K_S", + "33b-v1.1-q3_K_M", + "33b-v1.1-q3_K_L", + "33b-v1.1-q4_0", + "33b-v1.1-q4_1", + "33b-v1.1-q4_K_S", + "33b-v1.1-q4_K_M", + "33b-v1.1-q5_0", + "33b-v1.1-q5_1", + "33b-v1.1-q5_K_S", + "33b-v1.1-q5_K_M", + "33b-v1.1-q6_K", + "33b-v1.1-q8_0", + "33b-v1.1-fp16", + "34b-python", + "34b-python-q2_K", + "34b-python-q3_K_S", + "34b-python-q3_K_M", + "34b-python-q3_K_L", + "34b-python-q4_0", + "34b-python-q4_1", + "34b-python-q4_K_S", + "34b-python-q4_K_M", + "34b-python-q5_0", + "34b-python-q5_1", + "34b-python-q5_K_S", + "34b-python-q5_K_M", + "34b-python-q6_K", + "34b-python-q8_0", + "34b-python-fp16" + ], + "capabilities": [] + }, + "codegeex4": { + "tags": [ + "latest", + "9b", + "9b-all-q2_K", + "9b-all-q3_K_S", + "9b-all-q3_K_M", + "9b-all-q3_K_L", + "9b-all-q4_0", + "9b-all-q4_1", + "9b-all-q4_K_S", + "9b-all-q4_K_M", + "9b-all-q5_0", + "9b-all-q5_1", + "9b-all-q5_K_S", + "9b-all-q5_K_M", + "9b-all-q6_K", + "9b-all-q8_0", + "9b-all-fp16" + ], + "capabilities": [] + }, + "mistral-openorca": { + "tags": [ + "latest", + "7b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16" + ], + "capabilities": [] + }, + "sqlcoder": { + "tags": [ + "latest", + "7b", + "15b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "15b-q2_K", + "15b-q3_K_S", + "15b-q3_K_M", + "15b-q3_K_L", + "15b-q4_0", + "15b-q4_1", + "15b-q4_K_S", + "15b-q4_K_M", + "15b-q5_0", + "15b-q5_1", + "15b-q5_K_S", + "15b-q5_K_M", + "15b-q6_K", + "15b-q8_0", + "15b-fp16", + "70b-alpha-q2_K", + "70b-alpha-q3_K_S", + "70b-alpha-q3_K_M", + "70b-alpha-q3_K_L", + "70b-alpha-q4_0", + "70b-alpha-q4_1", + "70b-alpha-q4_K_S", + "70b-alpha-q4_K_M", + "70b-alpha-q5_0", + "70b-alpha-q5_1", + "70b-alpha-q5_K_S", + "70b-alpha-q5_K_M", + "70b-alpha-q6_K", + "70b-alpha-q8_0", + "70b-alpha-fp16" + ], + "capabilities": [] + }, + "deepseek-v3.1": { + "tags": [ + "latest", + "671b", + "671b-cloud", + "671b-terminus-q4_K_M", + "671b-terminus-q8_0", + "671b-terminus-fp16", + "671b-q8_0", + "671b-fp16" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "tinydolphin": { + "tags": [ + "latest", + "v2.8", + "1.1b", + "1.1b-v2.8-q2_K", + "1.1b-v2.8-q3_K_S", + "1.1b-v2.8-q3_K_M", + "1.1b-v2.8-q3_K_L", + "1.1b-v2.8-q4_0", + "1.1b-v2.8-q4_1", + "1.1b-v2.8-q4_K_S", + "1.1b-v2.8-q4_K_M", + "1.1b-v2.8-q5_0", + "1.1b-v2.8-q5_1", + "1.1b-v2.8-q5_K_S", + "1.1b-v2.8-q5_K_M", + "1.1b-v2.8-q6_K", + "1.1b-v2.8-q8_0", + "1.1b-v2.8-fp16" + ], + "capabilities": [] + }, + "stablelm2": { + "tags": [ + "latest", + "chat", + "zephyr", + "1.6b", + "12b", + "1.6b-chat", + "1.6b-chat-q2_K", + "1.6b-chat-q3_K_S", + "1.6b-chat-q3_K_M", + "1.6b-chat-q3_K_L", + "1.6b-chat-q4_0", + "1.6b-chat-q4_1", + "1.6b-chat-q4_K_S", + "1.6b-chat-q4_K_M", + "1.6b-chat-q5_0", + "1.6b-chat-q5_1", + "1.6b-chat-q5_K_S", + "1.6b-chat-q5_K_M", + "1.6b-chat-q6_K", + "1.6b-chat-q8_0", + "1.6b-chat-fp16", + "1.6b-zephyr", + "1.6b-zephyr-q2_K", + "1.6b-zephyr-q3_K_S", + "1.6b-zephyr-q3_K_M", + "1.6b-zephyr-q3_K_L", + "1.6b-zephyr-q4_0", + "1.6b-zephyr-q4_1", + "1.6b-zephyr-q4_K_S", + "1.6b-zephyr-q4_K_M", + "1.6b-zephyr-q5_0", + "1.6b-zephyr-q5_1", + "1.6b-zephyr-q5_K_S", + "1.6b-zephyr-q5_K_M", + "1.6b-zephyr-q6_K", + "1.6b-zephyr-q8_0", + "1.6b-zephyr-fp16", + "1.6b-q2_K", + "1.6b-q3_K_S", + "1.6b-q3_K_M", + "1.6b-q3_K_L", + "1.6b-q4_0", + "1.6b-q4_1", + "1.6b-q4_K_S", + "1.6b-q4_K_M", + "1.6b-q5_0", + "1.6b-q5_1", + "1.6b-q5_K_S", + "1.6b-q5_K_M", + "1.6b-q6_K", + "1.6b-q8_0", + "1.6b-fp16", + "12b-chat", + "12b-chat-q2_K", + "12b-chat-q3_K_S", + "12b-chat-q3_K_M", + "12b-chat-q3_K_L", + "12b-chat-q4_0", + "12b-chat-q4_1", + "12b-chat-q4_K_S", + "12b-chat-q4_K_M", + "12b-chat-q5_0", + "12b-chat-q5_1", + "12b-chat-q5_K_S", + "12b-chat-q5_K_M", + "12b-chat-q6_K", + "12b-chat-q8_0", + "12b-chat-fp16", + "12b-text", + "12b-q2_K", + "12b-q3_K_S", + "12b-q3_K_M", + "12b-q3_K_L", + "12b-q4_0", + "12b-q4_1", + "12b-q4_K_S", + "12b-q4_K_M", + "12b-q5_0", + "12b-q5_1", + "12b-q5_K_S", + "12b-q5_K_M", + "12b-q6_K", + "12b-q8_0", + "12b-fp16" + ], + "capabilities": [] + }, + "yi-coder": { + "tags": [ + "latest", + "1.5b", + "9b", + "1.5b-base", + "1.5b-base-q2_K", + "1.5b-base-q3_K_S", + "1.5b-base-q3_K_M", + "1.5b-base-q3_K_L", + "1.5b-base-q4_0", + "1.5b-base-q4_1", + "1.5b-base-q4_K_S", + "1.5b-base-q4_K_M", + "1.5b-base-q5_0", + "1.5b-base-q5_1", + "1.5b-base-q5_K_S", + "1.5b-base-q5_K_M", + "1.5b-base-q6_K", + "1.5b-base-q8_0", + "1.5b-base-fp16", + "1.5b-chat", + "1.5b-chat-q2_K", + "1.5b-chat-q3_K_S", + "1.5b-chat-q3_K_M", + "1.5b-chat-q3_K_L", + "1.5b-chat-q4_0", + "1.5b-chat-q4_1", + "1.5b-chat-q4_K_S", + "1.5b-chat-q4_K_M", + "1.5b-chat-q5_0", + "1.5b-chat-q5_1", + "1.5b-chat-q5_K_S", + "1.5b-chat-q5_K_M", + "1.5b-chat-q6_K", + "1.5b-chat-q8_0", + "1.5b-chat-fp16", + "9b-base", + "9b-base-q2_K", + "9b-base-q3_K_S", + "9b-base-q3_K_M", + "9b-base-q3_K_L", + "9b-base-q4_0", + "9b-base-q4_1", + "9b-base-q4_K_S", + "9b-base-q4_K_M", + "9b-base-q5_0", + "9b-base-q5_1", + "9b-base-q5_K_S", + "9b-base-q5_K_M", + "9b-base-q6_K", + "9b-base-q8_0", + "9b-base-fp16", + "9b-chat", + "9b-chat-q2_K", + "9b-chat-q3_K_S", + "9b-chat-q3_K_M", + "9b-chat-q3_K_L", + "9b-chat-q4_0", + "9b-chat-q4_1", + "9b-chat-q4_K_S", + "9b-chat-q4_K_M", + "9b-chat-q5_0", + "9b-chat-q5_1", + "9b-chat-q5_K_S", + "9b-chat-q5_K_M", + "9b-chat-q6_K", + "9b-chat-q8_0", + "9b-chat-fp16" + ], + "capabilities": [] + }, + "qwen3-next": { + "tags": [ + "latest", + "80b", + "80b-a3b-instruct-q4_K_M", + "80b-a3b-instruct-q8_0", + "80b-a3b-instruct-fp16", + "80b-a3b-thinking", + "80b-a3b-thinking-q4_K_M", + "80b-a3b-thinking-q8_0", + "80b-a3b-thinking-fp16", + "80b-cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "llama3-chatqa": { + "tags": [ + "latest", + "8b", + "70b", + "8b-v1.5", + "8b-v1.5-q2_K", + "8b-v1.5-q3_K_S", + "8b-v1.5-q3_K_M", + "8b-v1.5-q3_K_L", + "8b-v1.5-q4_0", + "8b-v1.5-q4_1", + "8b-v1.5-q4_K_S", + "8b-v1.5-q4_K_M", + "8b-v1.5-q5_0", + "8b-v1.5-q5_1", + "8b-v1.5-q5_K_S", + "8b-v1.5-q5_K_M", + "8b-v1.5-q6_K", + "8b-v1.5-q8_0", + "8b-v1.5-fp16", + "70b-v1.5", + "70b-v1.5-q2_K", + "70b-v1.5-q3_K_S", + "70b-v1.5-q3_K_M", + "70b-v1.5-q3_K_L", + "70b-v1.5-q4_0", + "70b-v1.5-q4_1", + "70b-v1.5-q4_K_S", + "70b-v1.5-q4_K_M", + "70b-v1.5-q5_0", + "70b-v1.5-q5_1", + "70b-v1.5-q5_K_S", + "70b-v1.5-q5_K_M", + "70b-v1.5-q6_K", + "70b-v1.5-q8_0", + "70b-v1.5-fp16" + ], + "capabilities": [] + }, + "granite3-dense": { + "tags": [ + "latest", + "2b", + "8b", + "2b-instruct-q2_K", + "2b-instruct-q3_K_S", + "2b-instruct-q3_K_M", + "2b-instruct-q3_K_L", + "2b-instruct-q4_0", + "2b-instruct-q4_1", + "2b-instruct-q4_K_S", + "2b-instruct-q4_K_M", + "2b-instruct-q5_0", + "2b-instruct-q5_1", + "2b-instruct-q5_K_S", + "2b-instruct-q5_K_M", + "2b-instruct-q6_K", + "2b-instruct-q8_0", + "2b-instruct-fp16", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-q4_0", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "granite3.1-dense": { + "tags": [ + "latest", + "2b", + "8b", + "2b-instruct-q2_K", + "2b-instruct-q3_K_S", + "2b-instruct-q3_K_M", + "2b-instruct-q3_K_L", + "2b-instruct-q4_0", + "2b-instruct-q4_1", + "2b-instruct-q4_K_S", + "2b-instruct-q4_K_M", + "2b-instruct-q5_0", + "2b-instruct-q5_1", + "2b-instruct-q5_K_S", + "2b-instruct-q5_K_M", + "2b-instruct-q6_K", + "2b-instruct-q8_0", + "2b-instruct-fp16", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-q4_0", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "wizard-math": { + "tags": [ + "latest", + "7b", + "13b", + "70b", + "7b-v1.1-q2_K", + "7b-v1.1-q3_K_S", + "7b-v1.1-q3_K_M", + "7b-v1.1-q3_K_L", + "7b-v1.1-q4_0", + "7b-v1.1-q4_1", + "7b-v1.1-q4_K_S", + "7b-v1.1-q4_K_M", + "7b-v1.1-q5_0", + "7b-v1.1-q5_1", + "7b-v1.1-q5_K_S", + "7b-v1.1-q5_K_M", + "7b-v1.1-q6_K", + "7b-v1.1-q8_0", + "7b-v1.1-fp16", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "70b-q2_K", + "70b-q3_K_S", + "70b-q3_K_M", + "70b-q3_K_L", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q4_K_M", + "70b-q5_0", + "70b-q5_1", + "70b-q5_K_S", + "70b-q5_K_M", + "70b-q6_K", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [] + }, + "dolphincoder": { + "tags": [ + "latest", + "7b", + "15b", + "7b-starcoder2", + "7b-starcoder2-q2_K", + "7b-starcoder2-q3_K_S", + "7b-starcoder2-q3_K_M", + "7b-starcoder2-q3_K_L", + "7b-starcoder2-q4_0", + "7b-starcoder2-q4_1", + "7b-starcoder2-q4_K_S", + "7b-starcoder2-q4_K_M", + "7b-starcoder2-q5_0", + "7b-starcoder2-q5_1", + "7b-starcoder2-q5_K_S", + "7b-starcoder2-q5_K_M", + "7b-starcoder2-q6_K", + "7b-starcoder2-q8_0", + "7b-starcoder2-fp16", + "15b-starcoder2", + "15b-starcoder2-q2_K", + "15b-starcoder2-q3_K_S", + "15b-starcoder2-q3_K_M", + "15b-starcoder2-q3_K_L", + "15b-starcoder2-q4_0", + "15b-starcoder2-q4_1", + "15b-starcoder2-q4_K_S", + "15b-starcoder2-q4_K_M", + "15b-starcoder2-q5_0", + "15b-starcoder2-q5_1", + "15b-starcoder2-q5_K_S", + "15b-starcoder2-q5_K_M", + "15b-starcoder2-q6_K", + "15b-starcoder2-q8_0", + "15b-starcoder2-fp16" + ], + "capabilities": [] + }, + "llama3-gradient": { + "tags": [ + "latest", + "instruct", + "1048k", + "8b", + "70b", + "8b-instruct-1048k-q2_K", + "8b-instruct-1048k-q3_K_S", + "8b-instruct-1048k-q3_K_M", + "8b-instruct-1048k-q3_K_L", + "8b-instruct-1048k-q4_0", + "8b-instruct-1048k-q4_1", + "8b-instruct-1048k-q4_K_S", + "8b-instruct-1048k-q4_K_M", + "8b-instruct-1048k-q5_0", + "8b-instruct-1048k-q5_1", + "8b-instruct-1048k-q5_K_S", + "8b-instruct-1048k-q5_K_M", + "8b-instruct-1048k-q6_K", + "8b-instruct-1048k-q8_0", + "8b-instruct-1048k-fp16", + "70b-instruct-1048k-q2_K", + "70b-instruct-1048k-q3_K_S", + "70b-instruct-1048k-q3_K_M", + "70b-instruct-1048k-q3_K_L", + "70b-instruct-1048k-q4_0", + "70b-instruct-1048k-q4_1", + "70b-instruct-1048k-q4_K_S", + "70b-instruct-1048k-q4_K_M", + "70b-instruct-1048k-q5_0", + "70b-instruct-1048k-q5_1", + "70b-instruct-1048k-q5_K_S", + "70b-instruct-1048k-q5_K_M", + "70b-instruct-1048k-q6_K", + "70b-instruct-1048k-q8_0", + "70b-instruct-1048k-fp16" + ], + "capabilities": [] + }, + "samantha-mistral": { + "tags": [ + "latest", + "7b", + "7b-instruct-q2_K", + "7b-instruct-q3_K_S", + "7b-instruct-q3_K_M", + "7b-instruct-q3_K_L", + "7b-instruct-q4_0", + "7b-instruct-q4_1", + "7b-instruct-q4_K_S", + "7b-instruct-q4_K_M", + "7b-instruct-q5_0", + "7b-instruct-q5_1", + "7b-instruct-q5_K_S", + "7b-instruct-q5_K_M", + "7b-instruct-q6_K", + "7b-instruct-q8_0", + "7b-instruct-fp16", + "7b-text", + "7b-text-q2_K", + "7b-text-q3_K_S", + "7b-text-q3_K_M", + "7b-text-q3_K_L", + "7b-text-q4_0", + "7b-text-q4_1", + "7b-text-q4_K_S", + "7b-text-q4_K_M", + "7b-text-q5_0", + "7b-text-q5_1", + "7b-text-q5_K_S", + "7b-text-q5_K_M", + "7b-text-q6_K", + "7b-text-q8_0", + "7b-text-fp16", + "7b-v1.2-text", + "7b-v1.2-text-q2_K", + "7b-v1.2-text-q3_K_S", + "7b-v1.2-text-q3_K_M", + "7b-v1.2-text-q3_K_L", + "7b-v1.2-text-q4_0", + "7b-v1.2-text-q4_1", + "7b-v1.2-text-q4_K_S", + "7b-v1.2-text-q4_K_M", + "7b-v1.2-text-q5_0", + "7b-v1.2-text-q5_1", + "7b-v1.2-text-q5_K_S", + "7b-v1.2-text-q5_K_M", + "7b-v1.2-text-q6_K", + "7b-v1.2-text-q8_0", + "7b-v1.2-text-fp16" + ], + "capabilities": [] + }, + "internlm2": { + "tags": [ + "latest", + "1m", + "1.8b", + "7b", + "20b", + "1.8b-chat-v2.5-q2_K", + "1.8b-chat-v2.5-q3_K_S", + "1.8b-chat-v2.5-q3_K_M", + "1.8b-chat-v2.5-q3_K_L", + "1.8b-chat-v2.5-q4_0", + "1.8b-chat-v2.5-q4_1", + "1.8b-chat-v2.5-q4_K_S", + "1.8b-chat-v2.5-q4_K_M", + "1.8b-chat-v2.5-q5_0", + "1.8b-chat-v2.5-q5_1", + "1.8b-chat-v2.5-q5_K_S", + "1.8b-chat-v2.5-q5_K_M", + "1.8b-chat-v2.5-q6_K", + "1.8b-chat-v2.5-q8_0", + "1.8b-chat-v2.5-fp16", + "7b-chat-1m-v2.5-q2_K", + "7b-chat-1m-v2.5-q3_K_S", + "7b-chat-1m-v2.5-q3_K_M", + "7b-chat-1m-v2.5-q3_K_L", + "7b-chat-1m-v2.5-q4_0", + "7b-chat-1m-v2.5-q4_1", + "7b-chat-1m-v2.5-q4_K_S", + "7b-chat-1m-v2.5-q4_K_M", + "7b-chat-1m-v2.5-q5_0", + "7b-chat-1m-v2.5-q5_1", + "7b-chat-1m-v2.5-q5_K_S", + "7b-chat-1m-v2.5-q5_K_M", + "7b-chat-1m-v2.5-q6_K", + "7b-chat-1m-v2.5-q8_0", + "7b-chat-1m-v2.5-fp16", + "7b-chat-v2.5-q2_K", + "7b-chat-v2.5-q3_K_S", + "7b-chat-v2.5-q3_K_M", + "7b-chat-v2.5-q3_K_L", + "7b-chat-v2.5-q4_0", + "7b-chat-v2.5-q4_1", + "7b-chat-v2.5-q4_K_S", + "7b-chat-v2.5-q4_K_M", + "7b-chat-v2.5-q5_0", + "7b-chat-v2.5-q5_1", + "7b-chat-v2.5-q5_K_S", + "7b-chat-v2.5-q5_K_M", + "7b-chat-v2.5-q6_K", + "7b-chat-v2.5-q8_0", + "7b-chat-v2.5-fp16", + "20b-chat-v2.5-q2_K", + "20b-chat-v2.5-q3_K_S", + "20b-chat-v2.5-q3_K_M", + "20b-chat-v2.5-q3_K_L", + "20b-chat-v2.5-q4_0", + "20b-chat-v2.5-q4_1", + "20b-chat-v2.5-q4_K_S", + "20b-chat-v2.5-q4_K_M", + "20b-chat-v2.5-q5_0", + "20b-chat-v2.5-q5_1", + "20b-chat-v2.5-q5_K_S", + "20b-chat-v2.5-q5_K_M", + "20b-chat-v2.5-q6_K", + "20b-chat-v2.5-q8_0", + "20b-chat-v2.5-fp16" + ], + "capabilities": [] + }, + "llama3-groq-tool-use": { + "tags": [ + "latest", + "8b", + "70b", + "8b-q2_K", + "8b-q3_K_S", + "8b-q3_K_M", + "8b-q3_K_L", + "8b-q4_0", + "8b-q4_1", + "8b-q4_K_S", + "8b-q4_K_M", + "8b-q5_0", + "8b-q5_1", + "8b-q5_K_S", + "8b-q5_K_M", + "8b-q6_K", + "8b-q8_0", + "8b-fp16", + "70b-q2_K", + "70b-q3_K_S", + "70b-q3_K_M", + "70b-q3_K_L", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q4_K_M", + "70b-q5_0", + "70b-q5_1", + "70b-q5_K_S", + "70b-q5_K_M", + "70b-q6_K", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "snowflake-arctic-embed2": { + "tags": [ + "latest", + "568m", + "568m-l-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "starling-lm": { + "tags": [ + "latest", + "alpha", + "beta", + "7b", + "7b-alpha", + "7b-alpha-q2_K", + "7b-alpha-q3_K_S", + "7b-alpha-q3_K_M", + "7b-alpha-q3_K_L", + "7b-alpha-q4_0", + "7b-alpha-q4_1", + "7b-alpha-q4_K_S", + "7b-alpha-q4_K_M", + "7b-alpha-q5_0", + "7b-alpha-q5_1", + "7b-alpha-q5_K_S", + "7b-alpha-q5_K_M", + "7b-alpha-q6_K", + "7b-alpha-q8_0", + "7b-alpha-fp16", + "7b-beta", + "7b-beta-q2_K", + "7b-beta-q3_K_S", + "7b-beta-q3_K_M", + "7b-beta-q3_K_L", + "7b-beta-q4_0", + "7b-beta-q4_1", + "7b-beta-q4_K_S", + "7b-beta-q4_K_M", + "7b-beta-q5_0", + "7b-beta-q5_1", + "7b-beta-q5_K_S", + "7b-beta-q5_K_M", + "7b-beta-q6_K", + "7b-beta-q8_0", + "7b-beta-fp16" + ], + "capabilities": [] + }, + "phind-codellama": { + "tags": [ + "latest", + "34b", + "34b-python", + "34b-python-q2_K", + "34b-python-q3_K_S", + "34b-python-q3_K_M", + "34b-python-q3_K_L", + "34b-python-q4_0", + "34b-python-q4_1", + "34b-python-q4_K_S", + "34b-python-q4_K_M", + "34b-python-q5_0", + "34b-python-q5_1", + "34b-python-q5_K_S", + "34b-python-q5_K_M", + "34b-python-q6_K", + "34b-python-q8_0", + "34b-python-fp16", + "34b-v2", + "34b-v2-q2_K", + "34b-v2-q3_K_S", + "34b-v2-q3_K_M", + "34b-v2-q3_K_L", + "34b-v2-q4_0", + "34b-v2-q4_1", + "34b-v2-q4_K_S", + "34b-v2-q4_K_M", + "34b-v2-q5_0", + "34b-v2-q5_1", + "34b-v2-q5_K_S", + "34b-v2-q5_K_M", + "34b-v2-q6_K", + "34b-v2-q8_0", + "34b-v2-fp16", + "34b-q2_K", + "34b-q3_K_S", + "34b-q3_K_M", + "34b-q3_K_L", + "34b-q4_0", + "34b-q4_1", + "34b-q4_K_S", + "34b-q4_K_M", + "34b-q5_0", + "34b-q5_1", + "34b-q5_K_S", + "34b-q5_K_M", + "34b-q6_K", + "34b-q8_0", + "34b-fp16" + ], + "capabilities": [] + }, + "solar": { + "tags": [ + "latest", + "10.7b", + "10.7b-instruct-v1-q2_K", + "10.7b-instruct-v1-q3_K_S", + "10.7b-instruct-v1-q3_K_M", + "10.7b-instruct-v1-q3_K_L", + "10.7b-instruct-v1-q4_0", + "10.7b-instruct-v1-q4_1", + "10.7b-instruct-v1-q4_K_S", + "10.7b-instruct-v1-q4_K_M", + "10.7b-instruct-v1-q5_0", + "10.7b-instruct-v1-q5_1", + "10.7b-instruct-v1-q5_K_S", + "10.7b-instruct-v1-q5_K_M", + "10.7b-instruct-v1-q6_K", + "10.7b-instruct-v1-q8_0", + "10.7b-instruct-v1-fp16", + "10.7b-text-v1-q2_K", + "10.7b-text-v1-q3_K_S", + "10.7b-text-v1-q3_K_M", + "10.7b-text-v1-q3_K_L", + "10.7b-text-v1-q4_0", + "10.7b-text-v1-q4_1", + "10.7b-text-v1-q4_K_S", + "10.7b-text-v1-q4_K_M", + "10.7b-text-v1-q5_0", + "10.7b-text-v1-q5_1", + "10.7b-text-v1-q5_K_S", + "10.7b-text-v1-q5_K_M", + "10.7b-text-v1-q6_K", + "10.7b-text-v1-q8_0", + "10.7b-text-v1-fp16" + ], + "capabilities": [] + }, + "granite3.2": { + "tags": [ + "latest", + "2b", + "8b", + "2b-instruct-q4_K_M", + "2b-instruct-q8_0", + "2b-instruct-fp16", + "8b-instruct-q4_K_M", + "8b-instruct-q8_0", + "8b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "llama-guard3": { + "tags": [ + "latest", + "1b", + "8b", + "1b-q2_K", + "1b-q3_K_S", + "1b-q3_K_M", + "1b-q3_K_L", + "1b-q4_0", + "1b-q4_1", + "1b-q4_K_S", + "1b-q4_K_M", + "1b-q5_0", + "1b-q5_1", + "1b-q5_K_S", + "1b-q5_K_M", + "1b-q6_K", + "1b-q8_0", + "1b-fp16", + "8b-q2_K", + "8b-q3_K_S", + "8b-q3_K_M", + "8b-q3_K_L", + "8b-q4_0", + "8b-q4_1", + "8b-q4_K_S", + "8b-q4_K_M", + "8b-q5_0", + "8b-q5_1", + "8b-q5_K_S", + "8b-q5_K_M", + "8b-q6_K", + "8b-q8_0", + "8b-fp16" + ], + "capabilities": [] + }, + "xwinlm": { + "tags": [ + "latest", + "7b", + "13b", + "7b-v0.1", + "7b-v0.1-q2_K", + "7b-v0.1-q3_K_S", + "7b-v0.1-q3_K_M", + "7b-v0.1-q3_K_L", + "7b-v0.1-q4_0", + "7b-v0.1-q4_1", + "7b-v0.1-q4_K_S", + "7b-v0.1-q4_K_M", + "7b-v0.1-q5_0", + "7b-v0.1-q5_1", + "7b-v0.1-q5_K_S", + "7b-v0.1-q5_K_M", + "7b-v0.1-q6_K", + "7b-v0.1-q8_0", + "7b-v0.1-fp16", + "7b-v0.2", + "7b-v0.2-q2_K", + "7b-v0.2-q3_K_S", + "7b-v0.2-q3_K_L", + "7b-v0.2-q4_0", + "7b-v0.2-q4_1", + "7b-v0.2-q4_K_S", + "7b-v0.2-q4_K_M", + "7b-v0.2-q5_0", + "7b-v0.2-q5_K_S", + "7b-v0.2-q5_K_M", + "7b-v0.2-q6_K", + "7b-v0.2-q8_0", + "7b-v0.2-fp16", + "13b-v0.1", + "13b-v0.1-q2_K", + "13b-v0.1-q3_K_S", + "13b-v0.1-q3_K_M", + "13b-v0.1-q3_K_L", + "13b-v0.1-q4_0", + "13b-v0.1-q4_1", + "13b-v0.1-q4_K_S", + "13b-v0.1-q4_K_M", + "13b-v0.1-q5_0", + "13b-v0.1-q5_1", + "13b-v0.1-q5_K_S", + "13b-v0.1-q5_K_M", + "13b-v0.1-q6_K", + "13b-v0.1-q8_0", + "13b-v0.1-fp16", + "13b-v0.2", + "13b-v0.2-q2_K", + "13b-v0.2-q3_K_S", + "13b-v0.2-q3_K_M", + "13b-v0.2-q3_K_L", + "13b-v0.2-q4_0", + "13b-v0.2-q4_1", + "13b-v0.2-q4_K_S", + "13b-v0.2-q4_K_M", + "13b-v0.2-q5_0", + "13b-v0.2-q5_1", + "13b-v0.2-q5_K_S", + "13b-v0.2-q5_K_M", + "13b-v0.2-q6_K", + "13b-v0.2-q8_0", + "13b-v0.2-fp16", + "70b-v0.1", + "70b-v0.1-q2_K", + "70b-v0.1-q3_K_S", + "70b-v0.1-q3_K_M", + "70b-v0.1-q3_K_L", + "70b-v0.1-q4_0", + "70b-v0.1-q4_1", + "70b-v0.1-q4_K_S", + "70b-v0.1-q4_K_M", + "70b-v0.1-q5_0", + "70b-v0.1-q5_1", + "70b-v0.1-q5_K_S", + "70b-v0.1-q6_K", + "70b-v0.1-q8_0", + "70b-v0.1-fp16" + ], + "capabilities": [] + }, + "aya-expanse": { + "tags": [ + "latest", + "8b", + "32b", + "8b-q2_K", + "8b-q3_K_S", + "8b-q3_K_M", + "8b-q3_K_L", + "8b-q4_0", + "8b-q4_1", + "8b-q4_K_S", + "8b-q4_K_M", + "8b-q5_0", + "8b-q5_1", + "8b-q5_K_S", + "8b-q5_K_M", + "8b-q6_K", + "8b-q8_0", + "8b-fp16", + "32b-q2_K", + "32b-q3_K_S", + "32b-q3_K_M", + "32b-q3_K_L", + "32b-q4_0", + "32b-q4_1", + "32b-q4_K_S", + "32b-q4_K_M", + "32b-q5_0", + "32b-q5_1", + "32b-q5_K_S", + "32b-q5_K_M", + "32b-q6_K", + "32b-q8_0", + "32b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "yarn-llama2": { + "tags": [ + "latest", + "7b", + "13b", + "7b-128k", + "7b-128k-q2_K", + "7b-128k-q3_K_S", + "7b-128k-q3_K_M", + "7b-128k-q3_K_L", + "7b-128k-q4_0", + "7b-128k-q4_1", + "7b-128k-q4_K_S", + "7b-128k-q4_K_M", + "7b-128k-q5_0", + "7b-128k-q5_1", + "7b-128k-q5_K_S", + "7b-128k-q5_K_M", + "7b-128k-q6_K", + "7b-128k-q8_0", + "7b-128k-fp16", + "7b-64k", + "7b-64k-q2_K", + "7b-64k-q3_K_S", + "7b-64k-q3_K_M", + "7b-64k-q3_K_L", + "7b-64k-q4_0", + "7b-64k-q4_1", + "7b-64k-q4_K_S", + "7b-64k-q4_K_M", + "7b-64k-q5_0", + "7b-64k-q5_1", + "7b-64k-q5_K_S", + "7b-64k-q5_K_M", + "7b-64k-q6_K", + "7b-64k-q8_0", + "7b-64k-fp16", + "13b-128k", + "13b-128k-q2_K", + "13b-128k-q3_K_S", + "13b-128k-q3_K_M", + "13b-128k-q3_K_L", + "13b-128k-q4_0", + "13b-128k-q4_1", + "13b-128k-q4_K_S", + "13b-128k-q4_K_M", + "13b-128k-q5_0", + "13b-128k-q5_1", + "13b-128k-q5_K_S", + "13b-128k-q5_K_M", + "13b-128k-q6_K", + "13b-128k-q8_0", + "13b-128k-fp16", + "13b-64k", + "13b-64k-q2_K", + "13b-64k-q3_K_S", + "13b-64k-q3_K_M", + "13b-64k-q3_K_L", + "13b-64k-q4_0", + "13b-64k-q4_1", + "13b-64k-q4_K_S", + "13b-64k-q4_K_M", + "13b-64k-q5_0", + "13b-64k-q5_1", + "13b-64k-q5_K_S", + "13b-64k-q5_K_M", + "13b-64k-q6_K", + "13b-64k-q8_0", + "13b-64k-fp16" + ], + "capabilities": [] + }, + "granite3-moe": { + "tags": [ + "latest", + "1b", + "3b", + "1b-instruct-q2_K", + "1b-instruct-q3_K_S", + "1b-instruct-q3_K_M", + "1b-instruct-q3_K_L", + "1b-instruct-q4_0", + "1b-instruct-q4_1", + "1b-instruct-q4_K_S", + "1b-instruct-q4_K_M", + "1b-instruct-q5_0", + "1b-instruct-q5_1", + "1b-instruct-q5_K_S", + "1b-instruct-q5_K_M", + "1b-instruct-q6_K", + "1b-instruct-q8_0", + "1b-instruct-fp16", + "3b-instruct-q2_K", + "3b-instruct-q3_K_S", + "3b-instruct-q3_K_M", + "3b-instruct-q3_K_L", + "3b-instruct-q4_0", + "3b-instruct-q4_1", + "3b-instruct-q4_K_S", + "3b-instruct-q4_K_M", + "3b-instruct-q5_0", + "3b-instruct-q5_1", + "3b-instruct-q5_K_S", + "3b-instruct-q5_K_M", + "3b-instruct-q6_K", + "3b-instruct-q8_0", + "3b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "reflection": { + "tags": [ + "latest", + "70b", + "70b-q2_K", + "70b-q3_K_S", + "70b-q3_K_M", + "70b-q3_K_L", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q4_K_M", + "70b-q5_0", + "70b-q5_1", + "70b-q5_K_S", + "70b-q5_K_M", + "70b-q6_K", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [] + }, + "orca2": { + "tags": [ + "latest", + "7b", + "13b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16" + ], + "capabilities": [] + }, + "r1-1776": { + "tags": [ + "latest", + "70b", + "671b", + "70b-distill-llama-q4_K_M", + "70b-distill-llama-q8_0", + "70b-distill-llama-fp16", + "671b-q4_K_M", + "671b-q8_0", + "671b-fp16" + ], + "capabilities": [] + }, + "stable-beluga": { + "tags": [ + "latest", + "7b", + "13b", + "70b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "70b-q2_K", + "70b-q3_K_S", + "70b-q3_K_M", + "70b-q3_K_L", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q4_K_M", + "70b-q5_0", + "70b-q5_1", + "70b-q5_K_S", + "70b-q5_K_M", + "70b-q6_K", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [] + }, + "exaone3.5": { + "tags": [ + "latest", + "2.4b", + "7.8b", + "32b", + "2.4b-instruct-q4_K_M", + "2.4b-instruct-q8_0", + "2.4b-instruct-fp16", + "7.8b-instruct-q4_K_M", + "7.8b-instruct-q8_0", + "7.8b-instruct-fp16", + "32b-instruct-q4_K_M", + "32b-instruct-q8_0", + "32b-instruct-fp16" + ], + "capabilities": [] + }, + "nemotron-mini": { + "tags": [ + "latest", + "4b", + "4b-instruct-q2_K", + "4b-instruct-q3_K_S", + "4b-instruct-q3_K_M", + "4b-instruct-q3_K_L", + "4b-instruct-q4_0", + "4b-instruct-q4_1", + "4b-instruct-q4_K_S", + "4b-instruct-q4_K_M", + "4b-instruct-q5_0", + "4b-instruct-q5_1", + "4b-instruct-q5_K_S", + "4b-instruct-q5_K_M", + "4b-instruct-q6_K", + "4b-instruct-q8_0", + "4b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "meditron": { + "tags": [ + "latest", + "7b", + "70b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q5_1" + ], + "capabilities": [] + }, + "reader-lm": { + "tags": [ + "latest", + "0.5b", + "1.5b", + "0.5b-q2_K", + "0.5b-q3_K_S", + "0.5b-q3_K_M", + "0.5b-q3_K_L", + "0.5b-q4_0", + "0.5b-q4_1", + "0.5b-q4_K_S", + "0.5b-q4_K_M", + "0.5b-q5_0", + "0.5b-q5_1", + "0.5b-q5_K_S", + "0.5b-q5_K_M", + "0.5b-q6_K", + "0.5b-q8_0", + "0.5b-fp16", + "1.5b-q2_K", + "1.5b-q3_K_S", + "1.5b-q3_K_M", + "1.5b-q3_K_L", + "1.5b-q4_0", + "1.5b-q4_1", + "1.5b-q4_K_S", + "1.5b-q4_K_M", + "1.5b-q5_0", + "1.5b-q5_1", + "1.5b-q5_K_S", + "1.5b-q5_K_M", + "1.5b-q6_K", + "1.5b-q8_0", + "1.5b-fp16" + ], + "capabilities": [] + }, + "shieldgemma": { + "tags": [ + "latest", + "2b", + "9b", + "27b", + "2b-q2_K", + "2b-q3_K_S", + "2b-q3_K_M", + "2b-q3_K_L", + "2b-q4_0", + "2b-q4_1", + "2b-q4_K_S", + "2b-q4_K_M", + "2b-q5_0", + "2b-q5_1", + "2b-q5_K_S", + "2b-q5_K_M", + "2b-q6_K", + "2b-q8_0", + "2b-fp16", + "9b-q2_K", + "9b-q3_K_S", + "9b-q3_K_M", + "9b-q3_K_L", + "9b-q4_0", + "9b-q4_1", + "9b-q4_K_S", + "9b-q4_K_M", + "9b-q5_0", + "9b-q5_1", + "9b-q5_K_S", + "9b-q5_K_M", + "9b-q6_K", + "9b-q8_0", + "9b-fp16", + "27b-q2_K", + "27b-q3_K_S", + "27b-q3_K_M", + "27b-q3_K_L", + "27b-q4_0", + "27b-q4_1", + "27b-q4_K_S", + "27b-q4_K_M", + "27b-q5_0", + "27b-q5_1", + "27b-q5_K_S", + "27b-q5_K_M", + "27b-q6_K", + "27b-q8_0", + "27b-fp16" + ], + "capabilities": [] + }, + "athene-v2": { + "tags": [ + "latest", + "72b", + "72b-q2_K", + "72b-q3_K_S", + "72b-q3_K_M", + "72b-q3_K_L", + "72b-q4_0", + "72b-q4_1", + "72b-q4_K_S", + "72b-q4_K_M", + "72b-q5_0", + "72b-q5_1", + "72b-q5_K_S", + "72b-q5_K_M", + "72b-q6_K", + "72b-q8_0", + "72b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "llama-pro": { + "tags": [ + "latest", + "instruct", + "text", + "8b-instruct-q2_K", + "8b-instruct-q3_K_S", + "8b-instruct-q3_K_M", + "8b-instruct-q3_K_L", + "8b-instruct-q4_0", + "8b-instruct-q4_1", + "8b-instruct-q4_K_S", + "8b-instruct-q4_K_M", + "8b-instruct-q5_0", + "8b-instruct-q5_1", + "8b-instruct-q5_K_S", + "8b-instruct-q5_K_M", + "8b-instruct-q6_K", + "8b-instruct-q8_0", + "8b-instruct-fp16", + "8b-text-q2_K", + "8b-text-q3_K_S", + "8b-text-q3_K_M", + "8b-text-q3_K_L", + "8b-text-q4_0", + "8b-text-q4_1", + "8b-text-q4_K_S", + "8b-text-q4_K_M", + "8b-text-q5_0", + "8b-text-q5_1", + "8b-text-q5_K_S", + "8b-text-q5_K_M", + "8b-text-q6_K", + "8b-text-q8_0", + "8b-text-fp16" + ], + "capabilities": [] + }, + "bge-large": { + "tags": [ + "latest", + "335m", + "335m-en-v1.5-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "nemotron": { + "tags": [ + "latest", + "70b", + "70b-instruct-q2_K", + "70b-instruct-q3_K_S", + "70b-instruct-q3_K_M", + "70b-instruct-q3_K_L", + "70b-instruct-q4_0", + "70b-instruct-q4_1", + "70b-instruct-q4_K_S", + "70b-instruct-q4_K_M", + "70b-instruct-q5_0", + "70b-instruct-q5_1", + "70b-instruct-q5_K_S", + "70b-instruct-q5_K_M", + "70b-instruct-q6_K", + "70b-instruct-q8_0", + "70b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "yarn-mistral": { + "tags": [ + "latest", + "7b", + "7b-128k", + "7b-128k-q2_K", + "7b-128k-q3_K_S", + "7b-128k-q3_K_M", + "7b-128k-q3_K_L", + "7b-128k-q4_0", + "7b-128k-q4_1", + "7b-128k-q4_K_S", + "7b-128k-q4_K_M", + "7b-128k-q5_0", + "7b-128k-q5_1", + "7b-128k-q5_K_S", + "7b-128k-q5_K_M", + "7b-128k-q6_K", + "7b-128k-q8_0", + "7b-128k-fp16", + "7b-64k", + "7b-64k-q2_K", + "7b-64k-q3_K_S", + "7b-64k-q3_K_M", + "7b-64k-q3_K_L", + "7b-64k-q4_0", + "7b-64k-q4_1", + "7b-64k-q4_K_S", + "7b-64k-q4_K_M", + "7b-64k-q5_0", + "7b-64k-q5_1", + "7b-64k-q5_K_S", + "7b-64k-q5_K_M", + "7b-64k-q6_K", + "7b-64k-q8_0" + ], + "capabilities": [] + }, + "wizardlm-uncensored": { + "tags": [ + "latest", + "13b", + "13b-llama2", + "13b-llama2-q2_K", + "13b-llama2-q3_K_S", + "13b-llama2-q3_K_M", + "13b-llama2-q3_K_L", + "13b-llama2-q4_0", + "13b-llama2-q4_1", + "13b-llama2-q4_K_S", + "13b-llama2-q4_K_M", + "13b-llama2-q5_0", + "13b-llama2-q5_1", + "13b-llama2-q5_K_S", + "13b-llama2-q5_K_M", + "13b-llama2-q6_K", + "13b-llama2-q8_0", + "13b-llama2-fp16" + ], + "capabilities": [] + }, + "nexusraven": { + "tags": [ + "latest", + "13b", + "13b-v2-q2_K", + "13b-v2-q3_K_S", + "13b-v2-q3_K_M", + "13b-v2-q3_K_L", + "13b-v2-q4_0", + "13b-v2-q4_1", + "13b-v2-q4_K_S", + "13b-v2-q4_K_M", + "13b-v2-q5_0", + "13b-v2-q5_1", + "13b-v2-q5_K_S", + "13b-v2-q5_K_M", + "13b-v2-q6_K", + "13b-v2-q8_0", + "13b-v2-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16" + ], + "capabilities": [] + }, + "wizardlm": { + "tags": [ + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16", + "13b-llama2-q2_K", + "13b-llama2-q3_K_S", + "13b-llama2-q3_K_M", + "13b-llama2-q3_K_L", + "13b-llama2-q4_0", + "13b-llama2-q4_1", + "13b-llama2-q4_K_S", + "13b-llama2-q4_K_M", + "13b-llama2-q5_0", + "13b-llama2-q5_1", + "13b-llama2-q5_K_S", + "13b-llama2-q5_K_M", + "13b-llama2-q6_K", + "13b-llama2-q8_0", + "13b-llama2-fp16", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16", + "30b-q2_K", + "30b-q3_K_S", + "30b-q3_K_M", + "30b-q3_K_L", + "30b-q4_0", + "30b-q4_1", + "30b-q4_K_S", + "30b-q4_K_M", + "30b-q5_0", + "30b-q5_1", + "30b-q5_K_S", + "30b-q5_K_M", + "30b-q6_K", + "30b-q8_0", + "30b-fp16", + "70b-llama2-q2_K", + "70b-llama2-q3_K_S", + "70b-llama2-q3_K_M", + "70b-llama2-q3_K_L", + "70b-llama2-q4_0", + "70b-llama2-q4_1", + "70b-llama2-q4_K_S", + "70b-llama2-q4_K_M", + "70b-llama2-q5_0", + "70b-llama2-q5_K_S", + "70b-llama2-q5_K_M", + "70b-llama2-q6_K", + "70b-llama2-q8_0" + ], + "capabilities": [] + }, + "llava-phi3": { + "tags": [ + "latest", + "3.8b", + "3.8b-mini-q4_0", + "3.8b-mini-fp16" + ], + "capabilities": [ + "vision" + ] + }, + "granite-embedding": { + "tags": [ + "latest", + "30m", + "278m", + "30m-en", + "30m-en-fp16", + "278m-fp16" + ], + "capabilities": [ + "embedding" + ] + }, + "tulu3": { + "tags": [ + "latest", + "8b", + "70b", + "8b-q4_K_M", + "8b-q8_0", + "8b-fp16", + "70b-q4_K_M", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [] + }, + "medllama2": { + "tags": [ + "latest", + "7b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16" + ], + "capabilities": [] + }, + "nous-hermes2-mixtral": { + "tags": [ + "latest", + "dpo", + "8x7b", + "8x7b-dpo-q2_K", + "8x7b-dpo-q3_K_S", + "8x7b-dpo-q3_K_M", + "8x7b-dpo-q3_K_L", + "8x7b-dpo-q4_0", + "8x7b-dpo-q4_1", + "8x7b-dpo-q4_K_S", + "8x7b-dpo-q4_K_M", + "8x7b-dpo-q5_0", + "8x7b-dpo-q5_1", + "8x7b-dpo-q5_K_S", + "8x7b-dpo-q5_K_M", + "8x7b-dpo-q6_K", + "8x7b-dpo-q8_0", + "8x7b-dpo-fp16" + ], + "capabilities": [] + }, + "dbrx": { + "tags": [ + "latest", + "instruct", + "132b", + "132b-instruct-q2_K", + "132b-instruct-q4_0", + "132b-instruct-q8_0", + "132b-instruct-fp16" + ], + "capabilities": [] + }, + "codeup": { + "tags": [ + "latest", + "13b", + "13b-llama2", + "13b-llama2-chat", + "13b-llama2-chat-q2_K", + "13b-llama2-chat-q3_K_S", + "13b-llama2-chat-q3_K_M", + "13b-llama2-chat-q3_K_L", + "13b-llama2-chat-q4_0", + "13b-llama2-chat-q4_1", + "13b-llama2-chat-q4_K_S", + "13b-llama2-chat-q4_K_M", + "13b-llama2-chat-q5_0", + "13b-llama2-chat-q5_1", + "13b-llama2-chat-q5_K_S", + "13b-llama2-chat-q5_K_M", + "13b-llama2-chat-q6_K", + "13b-llama2-chat-q8_0", + "13b-llama2-chat-fp16" + ], + "capabilities": [] + }, + "everythinglm": { + "tags": [ + "latest", + "13b", + "13b-16k", + "13b-16k-q2_K", + "13b-16k-q3_K_S", + "13b-16k-q3_K_M", + "13b-16k-q3_K_L", + "13b-16k-q4_0", + "13b-16k-q4_1", + "13b-16k-q4_K_S", + "13b-16k-q4_K_M", + "13b-16k-q5_0", + "13b-16k-q5_1", + "13b-16k-q5_K_S", + "13b-16k-q5_K_M", + "13b-16k-q6_K", + "13b-16k-q8_0", + "13b-16k-fp16" + ], + "capabilities": [] + }, + "mathstral": { + "tags": [ + "latest", + "7b", + "7b-v0.1-q2_K", + "7b-v0.1-q3_K_S", + "7b-v0.1-q3_K_M", + "7b-v0.1-q3_K_L", + "7b-v0.1-q4_0", + "7b-v0.1-q4_1", + "7b-v0.1-q4_K_S", + "7b-v0.1-q4_K_M", + "7b-v0.1-q5_0", + "7b-v0.1-q5_1", + "7b-v0.1-q5_K_S", + "7b-v0.1-q5_K_M", + "7b-v0.1-q6_K", + "7b-v0.1-q8_0", + "7b-v0.1-fp16" + ], + "capabilities": [] + }, + "solar-pro": { + "tags": [ + "latest", + "preview", + "22b", + "22b-preview-instruct-q2_K", + "22b-preview-instruct-q3_K_S", + "22b-preview-instruct-q3_K_M", + "22b-preview-instruct-q3_K_L", + "22b-preview-instruct-q4_0", + "22b-preview-instruct-q4_1", + "22b-preview-instruct-q4_K_S", + "22b-preview-instruct-q4_K_M", + "22b-preview-instruct-q5_0", + "22b-preview-instruct-q5_1", + "22b-preview-instruct-q5_K_S", + "22b-preview-instruct-q5_K_M", + "22b-preview-instruct-q6_K", + "22b-preview-instruct-q8_0", + "22b-preview-instruct-fp16" + ], + "capabilities": [] + }, + "stablelm-zephyr": { + "tags": [ + "latest", + "3b", + "3b-q2_K", + "3b-q3_K_S", + "3b-q3_K_M", + "3b-q3_K_L", + "3b-q4_0", + "3b-q4_1", + "3b-q4_K_S", + "3b-q4_K_M", + "3b-q5_0", + "3b-q5_1", + "3b-q5_K_S", + "3b-q5_K_M", + "3b-q6_K", + "3b-q8_0", + "3b-fp16" + ], + "capabilities": [] + }, + "falcon2": { + "tags": [ + "latest", + "11b", + "11b-q2_K", + "11b-q3_K_S", + "11b-q3_K_M", + "11b-q3_K_L", + "11b-q4_0", + "11b-q4_1", + "11b-q4_K_S", + "11b-q4_K_M", + "11b-q5_0", + "11b-q5_1", + "11b-q5_K_S", + "11b-q5_K_M", + "11b-q6_K", + "11b-q8_0", + "11b-fp16" + ], + "capabilities": [] + }, + "magicoder": { + "tags": [ + "latest", + "7b", + "7b-s-cl", + "7b-s-cl-q2_K", + "7b-s-cl-q3_K_S", + "7b-s-cl-q3_K_M", + "7b-s-cl-q3_K_L", + "7b-s-cl-q4_0", + "7b-s-cl-q4_1", + "7b-s-cl-q4_K_S", + "7b-s-cl-q4_K_M", + "7b-s-cl-q5_0", + "7b-s-cl-q5_1", + "7b-s-cl-q5_K_S", + "7b-s-cl-q5_K_M", + "7b-s-cl-q6_K", + "7b-s-cl-q8_0", + "7b-s-cl-fp16" + ], + "capabilities": [] + }, + "duckdb-nsql": { + "tags": [ + "latest", + "7b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16" + ], + "capabilities": [] + }, + "smallthinker": { + "tags": [ + "latest", + "3b", + "3b-preview-q4_K_M", + "3b-preview-q8_0", + "3b-preview-fp16" + ], + "capabilities": [] + }, + "mistrallite": { + "tags": [ + "latest", + "7b", + "7b-v0.1-q2_K", + "7b-v0.1-q3_K_S", + "7b-v0.1-q3_K_M", + "7b-v0.1-q3_K_L", + "7b-v0.1-q4_0", + "7b-v0.1-q4_1", + "7b-v0.1-q4_K_S", + "7b-v0.1-q4_K_M", + "7b-v0.1-q5_0", + "7b-v0.1-q5_1", + "7b-v0.1-q5_K_S", + "7b-v0.1-q5_K_M", + "7b-v0.1-q6_K", + "7b-v0.1-q8_0", + "7b-v0.1-fp16" + ], + "capabilities": [] + }, + "nuextract": { + "tags": [ + "latest", + "3.8b", + "3.8b-q2_K", + "3.8b-q3_K_S", + "3.8b-q3_K_M", + "3.8b-q3_K_L", + "3.8b-q4_0", + "3.8b-q4_1", + "3.8b-q4_K_S", + "3.8b-q4_K_M", + "3.8b-q5_0", + "3.8b-q5_1", + "3.8b-q5_K_S", + "3.8b-q5_K_M", + "3.8b-q6_K", + "3.8b-q8_0", + "3.8b-fp16" + ], + "capabilities": [] + }, + "bespoke-minicheck": { + "tags": [ + "latest", + "7b", + "7b-q2_K", + "7b-q3_K_S", + "7b-q3_K_M", + "7b-q3_K_L", + "7b-q4_0", + "7b-q4_1", + "7b-q4_K_S", + "7b-q4_K_M", + "7b-q5_0", + "7b-q5_1", + "7b-q5_K_S", + "7b-q5_K_M", + "7b-q6_K", + "7b-q8_0", + "7b-fp16" + ], + "capabilities": [] + }, + "codebooga": { + "tags": [ + "latest", + "34b", + "34b-v0.1-q2_K", + "34b-v0.1-q3_K_S", + "34b-v0.1-q3_K_M", + "34b-v0.1-q3_K_L", + "34b-v0.1-q4_0", + "34b-v0.1-q4_1", + "34b-v0.1-q4_K_M", + "34b-v0.1-q5_0", + "34b-v0.1-q5_1", + "34b-v0.1-q5_K_S", + "34b-v0.1-q5_K_M", + "34b-v0.1-q6_K", + "34b-v0.1-q8_0", + "34b-v0.1-fp16" + ], + "capabilities": [] + }, + "megadolphin": { + "tags": [ + "latest", + "v2.2", + "120b", + "120b-v2.2", + "120b-v2.2-q2_K", + "120b-v2.2-q3_K_S", + "120b-v2.2-q3_K_M", + "120b-v2.2-q3_K_L", + "120b-v2.2-q4_0", + "120b-v2.2-q4_1", + "120b-v2.2-q4_K_S", + "120b-v2.2-q4_K_M", + "120b-v2.2-q5_0", + "120b-v2.2-q5_1", + "120b-v2.2-q5_K_S", + "120b-v2.2-q5_K_M", + "120b-v2.2-q6_K", + "120b-v2.2-q8_0", + "120b-v2.2-fp16" + ], + "capabilities": [] + }, + "wizard-vicuna": { + "tags": [ + "latest", + "13b", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16" + ], + "capabilities": [] + }, + "command-r7b": { + "tags": [ + "latest", + "7b", + "7b-12-2024-q4_K_M", + "7b-12-2024-q8_0", + "7b-12-2024-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "phi4-mini-reasoning": { + "tags": [ + "latest", + "3.8b", + "3.8b-q4_K_M", + "3.8b-q8_0", + "3.8b-fp16" + ], + "capabilities": [] + }, + "deepseek-v2.5": { + "tags": [ + "latest", + "236b", + "236b-q4_0", + "236b-q4_1", + "236b-q5_0", + "236b-q5_1", + "236b-q8_0" + ], + "capabilities": [] + }, + "notux": { + "tags": [ + "latest", + "8x7b", + "8x7b-v1", + "8x7b-v1-q2_K", + "8x7b-v1-q3_K_S", + "8x7b-v1-q3_K_M", + "8x7b-v1-q3_K_L", + "8x7b-v1-q4_0", + "8x7b-v1-q4_1", + "8x7b-v1-q4_K_S", + "8x7b-v1-q4_K_M", + "8x7b-v1-q5_0", + "8x7b-v1-q5_1", + "8x7b-v1-q5_K_S", + "8x7b-v1-q5_K_M", + "8x7b-v1-q6_K", + "8x7b-v1-q8_0", + "8x7b-v1-fp16" + ], + "capabilities": [] + }, + "notus": { + "tags": [ + "latest", + "7b", + "7b-v1", + "7b-v1-q2_K", + "7b-v1-q3_K_S", + "7b-v1-q3_K_M", + "7b-v1-q3_K_L", + "7b-v1-q4_0", + "7b-v1-q4_1", + "7b-v1-q4_K_S", + "7b-v1-q4_K_M", + "7b-v1-q5_0", + "7b-v1-q5_1", + "7b-v1-q5_K_S", + "7b-v1-q5_K_M", + "7b-v1-q6_K", + "7b-v1-q8_0", + "7b-v1-fp16" + ], + "capabilities": [] + }, + "firefunction-v2": { + "tags": [ + "latest", + "70b", + "70b-q2_K", + "70b-q3_K_S", + "70b-q3_K_M", + "70b-q3_K_L", + "70b-q4_0", + "70b-q4_1", + "70b-q4_K_S", + "70b-q4_K_M", + "70b-q5_0", + "70b-q5_1", + "70b-q5_K_S", + "70b-q5_K_M", + "70b-q6_K", + "70b-q8_0", + "70b-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "open-orca-platypus2": { + "tags": [ + "latest", + "13b", + "13b-q2_K", + "13b-q3_K_S", + "13b-q3_K_M", + "13b-q3_K_L", + "13b-q4_0", + "13b-q4_1", + "13b-q4_K_S", + "13b-q4_K_M", + "13b-q5_0", + "13b-q5_1", + "13b-q5_K_S", + "13b-q5_K_M", + "13b-q6_K", + "13b-q8_0", + "13b-fp16" + ], + "capabilities": [] + }, + "goliath": { + "tags": [ + "latest", + "120b-q2_K", + "120b-q3_K_S", + "120b-q3_K_M", + "120b-q3_K_L", + "120b-q4_0", + "120b-q4_1", + "120b-q4_K_S", + "120b-q4_K_M", + "120b-q5_0", + "120b-q5_1", + "120b-q5_K_S", + "120b-q5_K_M", + "120b-q6_K", + "120b-q8_0", + "120b-fp16" + ], + "capabilities": [] + }, + "command-a": { + "tags": [ + "latest", + "111b", + "111b-03-2025-q4_K_M", + "111b-03-2025-q8_0", + "111b-03-2025-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "deepseek-ocr": { + "tags": [ + "latest", + "3b", + "3b-bf16" + ], + "capabilities": [ + "vision" + ] + }, + "sailor2": { + "tags": [ + "latest", + "1b", + "8b", + "20b", + "1b-chat-q4_K_M", + "1b-chat-q8_0", + "1b-chat-fp16", + "8b-chat-q4_K_M", + "8b-chat-q8_0", + "8b-chat-fp16", + "20b-chat-q4_K_M", + "20b-chat-q8_0", + "20b-chat-fp16" + ], + "capabilities": [] + }, + "granite3-guardian": { + "tags": [ + "latest", + "2b", + "8b", + "2b-q8_0", + "2b-fp16", + "8b-q5_K_S", + "8b-q5_K_M", + "8b-q6_K", + "8b-q8_0", + "8b-fp16" + ], + "capabilities": [] + }, + "marco-o1": { + "tags": [ + "latest", + "7b", + "7b-q4_K_M", + "7b-q8_0", + "7b-fp16" + ], + "capabilities": [] + }, + "gemini-3-pro-preview": { + "tags": [ + "latest" + ], + "capabilities": [ + "vision", + "tools", + "thinking" + ] + }, + "alfred": { + "tags": [ + "latest", + "40b", + "40b-1023-q4_0", + "40b-1023-q4_1", + "40b-1023-q5_0", + "40b-1023-q5_1", + "40b-1023-q8_0" + ], + "capabilities": [] + }, + "command-r7b-arabic": { + "tags": [ + "latest", + "7b", + "7b-02-2025-q4_K_M", + "7b-02-2025-q8_0", + "7b-02-2025-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "gpt-oss-safeguard": { + "tags": [ + "latest", + "20b", + "120b" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "glm-4.6": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "olmo-3.1": { + "tags": [ + "latest", + "32b", + "32b-instruct", + "32b-instruct-q4_K_M", + "32b-instruct-q8_0", + "32b-instruct-fp16", + "32b-think", + "32b-think-q4_K_M", + "32b-think-q8_0", + "32b-think-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "cogito-2.1": { + "tags": [ + "latest", + "671b", + "671b-cloud", + "671b-q4_K_M", + "671b-q8_0", + "671b-fp16" + ], + "capabilities": [] + }, + "minimax-m2": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "rnj-1": { + "tags": [ + "latest", + "8b", + "8b-cloud", + "8b-instruct-q4_K_M", + "8b-instruct-q8_0", + "8b-instruct-fp16" + ], + "capabilities": [ + "tools" + ] + }, + "kimi-k2": { + "tags": [ + "1t-cloud" + ], + "capabilities": [ + "tools" + ] + }, + "kimi-k2-thinking": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "nomic-embed-text-v2-moe": { + "tags": [ + "latest" + ], + "capabilities": [ + "embedding" + ] + }, + "deepseek-v3.2": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "glm-4.7": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools", + "thinking" + ] + }, + "mistral-large-3": { + "tags": [ + "675b-cloud" + ], + "capabilities": [ + "vision", + "tools" + ] + }, + "minimax-m2.1": { + "tags": [ + "cloud" + ], + "capabilities": [ + "tools" + ] + } } } \ No newline at end of file diff --git a/scripts/scrape-ollama-models.mjs b/scripts/scrape-ollama-models.mjs index 93d1cc7..b90f0af 100644 --- a/scripts/scrape-ollama-models.mjs +++ b/scripts/scrape-ollama-models.mjs @@ -14,29 +14,45 @@ const __dirname = dirname(fileURLToPath(import.meta.url)); const OLLAMA_LIBRARY_URL = 'https://ollama.com/library'; /** - * Fetches the list of all available model names from Ollama's library page + * Fetches the list of all available models with their capabilities from Ollama's library page + * @returns {Promise>} */ -async function fetchModelNames() { +async function fetchModelsWithCapabilities() { console.log('Fetching model list from Ollama library...'); const response = await fetch(OLLAMA_LIBRARY_URL); const html = await response.text(); - // Extract model names using regex (matches href="/library/modelname") - const modelRegex = /href="\/library\/([^"\/]+)"/g; - const models = new Set(); - let match; + // Parse models and their capabilities from the HTML + // Each model is in a
  • block + const modelBlocks = html.split('
  • ]*>([^<]+) { + batch.map(async ({ name, capabilities }) => { const tags = await fetchModelTags(name); - return { name, tags }; + return { name, tags, capabilities }; }) ); - for (const { name, tags } of results) { - models[name] = tags; - console.log(` ${name}: ${tags.length} tags`); + for (const { name, tags, capabilities } of results) { + models[name] = { + tags, + capabilities, + }; + console.log(` ${name}: ${tags.length} tags, capabilities: [${capabilities.join(', ')}]`); } }