Top 100
Models ordered by hosted inventory, most hosted files first, then A–Z. Not a popularity chart.
Showing stale catalog ·
| Type | Model | Recorded size | Downloads | Updated |
|---|---|---|---|---|
14B Qwen2.5 Kunou v1Sao10K/14B-Qwen2.5-Kunou-v1The catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Sao10K on Hugging Face. File format: Safetensors.
| 29.5 GB | 285 downloads on Hugging Face | 2026-09-19 | |
14B Qwen2.5 Freya x1Sao10K/14B-Qwen2.5-Freya-x1The catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Sao10K on Hugging Face. File format: Safetensors.
| 29.5 GB | 33 downloads on Hugging Face | 2026-09-19 | |
DeepSeek Coder V2 Lite FP8RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8The catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: RedHatAI on Hugging Face. File format: Safetensors.
| 16.1 GB | 125,856 downloads on Hugging Face | 2026-09-21 | |
Forgotten Safeword v1.1 22BReadyArt/Forgotten-Safeword-v1.1-22BThe catalog does not give enough information to describe what this model is for. Catalog source: unknown.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.Source: ReadyArt on Hugging Face. File format: Safetensors.
| 44.5 GB | 9 downloads on Hugging Face | 2026-09-19 | |
Forgotten Abomination 24B v1.2ReadyArt/Forgotten-Abomination-24B-v1.2The catalog does not give enough information to describe what this model is for. Catalog source: unknown.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.Source: ReadyArt on Hugging Face. File format: Safetensors.
| 47.1 GB | 12 downloads on Hugging Face | 2026-09-19 | |
Fever Dream 22B v1.1ReadyArt/Fever-Dream-22B-v1.1The catalog does not give enough information to describe what this model is for. Catalog source: unknown.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.Source: ReadyArt on Hugging Face. File format: Safetensors.
| 44.5 GB | 5 downloads on Hugging Face | 2026-09-19 | |
Meta Llama 3 8B iMatqwp4w3hyb/Meta-Llama-3-8B-Instruct-iMat-GGUFThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: qwp4w3hyb on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 5,657 downloads on Hugging Face | 2026-09-18 | |
Qwen3 Omni 30B A3BQwen/Qwen3-Omni-30B-A3B-InstructThe catalog lists this model for generating audio from text. Catalog sources: license, tags.Content controls: not assessed.DetailsThe catalog lists this model for generating audio from text.See the publisher’s description →Source: Qwen on Hugging Face. File format: Safetensors.
| 70.5 GB | 689,177 downloads on Hugging Face | 2025-09-22 | |
Qwen2.5 VL 72BQwen/Qwen2.5-VL-72B-InstructThe catalog lists this model for generating text from images and text. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: Qwen on Hugging Face. File format: Safetensors.
| 146.8 GB | 98,438 downloads on Hugging Face | 2025-06-06 | |
Qwen2.5 Math PRM 7BQwen/Qwen2.5-Math-PRM-7BThe catalog lists this model for sorting text into categories. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for sorting text into categories.Source: Qwen on Hugging Face. File format: Safetensors.
| 15.3 GB | 86,691 downloads on Hugging Face | 2026-09-21 | |
Qwen2.5 Coder 3BQwen/Qwen2.5-Coder-3B-Instruct-AWQThe catalog lists this model for working with code. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for working with code.Source: Qwen on Hugging Face. File format: Safetensors.
| 2.69 GB | 16,406 downloads on Hugging Face | 2026-09-21 | |
Qwen2.5 Coder 3BQwen/Qwen2.5-Coder-3B-InstructThe catalog lists this model for working with code. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for working with code.Source: Qwen on Hugging Face. File format: Safetensors.
| 6.17 GB | 603,615 downloads on Hugging Face | 2026-09-20 | |
Qwen2.5 72BQwen/Qwen2.5-72B-InstructThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 145.4 GB | 356,394 downloads on Hugging Face | 2025-01-12 | |
Qwen2.5 3BQwen/Qwen2.5-3B-Instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 2.1 GB | 324,592 downloads on Hugging Face | 2026-09-18 | |
Qwen2.5 3BQwen/Qwen2.5-3B-Instruct-AWQThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 2.69 GB | 426,674 downloads on Hugging Face | 2026-09-20 | |
Qwen2.5 3BQwen/Qwen2.5-3B-InstructThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 6.17 GB | 5,284,682 downloads on Hugging Face | 2026-09-20 | |
Qwen2.5 3BQwen/Qwen2.5-3BThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 6.17 GB | 338,459 downloads on Hugging Face | 2026-09-20 | |
Qwen1.5 MoE A2.7BQwen/Qwen1.5-MoE-A2.7B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 28.6 GB | 36,704 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 MoE A2.7BQwen/Qwen1.5-MoE-A2.7BThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 28.6 GB | 672,842 downloads on Hugging Face | 2026-09-20 | |
Qwen1.5 7BQwen/Qwen1.5-7B-Chat-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.77 GB | 12,431 downloads on Hugging Face | 2026-09-18 | |
Qwen1.5 7BQwen/Qwen1.5-7BThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 15.4 GB | 91,636 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 4BQwen/Qwen1.5-4B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 7.9 GB | 17,442 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 32BQwen/Qwen1.5-32B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 65 GB | 50,803 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 1.8BQwen/Qwen1.5-1.8B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 3.67 GB | 50,018 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 14BQwen/Qwen1.5-14B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 28.3 GB | 12,981 downloads on Hugging Face | 2026-09-21 | |
Qwen1.5 0.5BQwen/Qwen1.5-0.5B-Chat-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 407.2 MB | 10,769 downloads on Hugging Face | 2024-04-09 | |
Qwen1.5 0.5BQwen/Qwen1.5-0.5BThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 1.24 GB | 46,063 downloads on Hugging Face | 2026-09-21 | |
CodeQwen1.5 7BQwen/CodeQwen1.5-7B-ChatThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 14.5 GB | 9,633 downloads on Hugging Face | 2026-09-21 | |
suzume llama 3 8B multilingualQuantFactory/suzume-llama-3-8B-multilingual-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,036 downloads on Hugging Face | 2024-04-25 | |
saiga llama3 8BQuantFactory/saiga_llama3_8b-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,647 downloads on Hugging Face | 2026-09-18 | |
Qwen2.5 3BQuantFactory/Qwen2.5-3B-Instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 1.93 GB | 1,177 downloads on Hugging Face | 2026-09-19 | |
Meta Llama Guard 2 8BQuantFactory/Meta-Llama-Guard-2-8B-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 806 downloads on Hugging Face | 2026-09-19 | |
Meta Llama 3 8B GGUF v2QuantFactory/Meta-Llama-3-8B-Instruct-GGUF-v2The catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 962 downloads on Hugging Face | 2026-09-19 | |
Meta Llama 3 8BQuantFactory/Meta-Llama-3-8B-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,750 downloads on Hugging Face | 2026-09-19 | |
Llama 3 SauerkrautLM 8BQuantFactory/Llama-3-SauerkrautLM-8b-Instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 866 downloads on Hugging Face | 2026-09-19 | |
Llama 3 Open Ko 8BQuantFactory/Llama-3-Open-Ko-8B-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,025 downloads on Hugging Face | 2026-09-19 | |
Llama 3 Alpha Ko 8BQuantFactory/Llama-3-Alpha-Ko-8B-Instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,419 downloads on Hugging Face | 2026-09-19 | |
Llama 3 8B LexiFun Uncensored V1QuantFactory/Llama-3-8B-LexiFun-Uncensored-V1-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,821 downloads on Hugging Face | 2026-09-19 | |
Llama 3 8B Replete AdaptedQuantFactory/Llama3-8B-Instruct-Replete-Adapted-GGUFThe catalog lists this model for generating text. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for generating text.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 923 downloads on Hugging Face | 2026-09-19 | |
Llama 3 8B ChineseQuantFactory/Llama3-8B-Chinese-Chat-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 1,106 downloads on Hugging Face | 2026-09-19 | |
Llama 3 13BQuantFactory/Llama-3-13B-Instruct-v0.1-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 8.06 GB | 1,066 downloads on Hugging Face | 2026-09-19 | |
glm 4 9BQuantFactory/glm-4-9b-chat-GGUFThe catalog lists this model for having conversations. Catalog sources: tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 6.25 GB | 840 downloads on Hugging Face | 2026-09-19 | |
Dolphin3.0 Qwen2.5 3BQuantFactory/Dolphin3.0-Qwen2.5-3b-GGUFThe catalog does not give enough information to describe what this model is for. Catalog source: unknown.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 2.1 GB | 1,442 downloads on Hugging Face | 2026-09-19 | |
deepseek math 7B rlQuantFactory/deepseek-math-7b-rl-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.92 GB | 867 downloads on Hugging Face | 2026-09-19 | |
deepseek math 7BQuantFactory/deepseek-math-7b-instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.22 GB | 1,334 downloads on Hugging Face | 2026-09-19 | |
DeepSeek Coder V2 LiteQuantFactory/DeepSeek-Coder-V2-Lite-Instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 10.4 GB | 1,008 downloads on Hugging Face | 2026-09-19 | |
DeepSeek Coder V2 Lite BaseQuantFactory/DeepSeek-Coder-V2-Lite-Base-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 10.4 GB | 945 downloads on Hugging Face | 2026-09-19 | |
deepseek coder 6.7BQuantFactory/deepseek-coder-6.7b-instruct-GGUFThe catalog lists this model for having conversations. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 4.08 GB | 1,722 downloads on Hugging Face | 2026-09-18 | |
Cotype NanoQuantFactory/Cotype-Nano-GGUFThe catalog lists this model for having conversations. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 986 MB | 14,048 downloads on Hugging Face | 2026-09-18 | |
Codestral 22B v0.1QuantFactory/Codestral-22B-v0.1-GGUFThe catalog lists this model for working with code. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for working with code.Source: QuantFactory on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 13.3 GB | 1,037 downloads on Hugging Face | 2024-05-30 |