unsloth AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 764
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 68.8M
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 416.5M
- Total likes
- 53.8K
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- —
Most downloaded
- 1Qwen3-Coder-30B-A3B-Instruct-GGUFJan 30, 202612.7M
- 2Qwen3.8-27B-GGUFAug 20, 20266.7M
- 3Qwen3.6-27B-NVFP4Jul 12, 20263.8M
- 4Qwen3.6-35B-A3B-NVFP4Jul 12, 20262.6M
- 5Qwen3.5-9B-GGUFMar 2, 20261.4M
- 6Qwen3.8-27B-NVFP4Aug 17, 20261.3M
- 7Qwen3-30B-A3B-Thinking-2507-GGUFJul 31, 20251.3M
- 8Qwen3.6-35B-A3B-GGUFApr 20, 20261.2M
- 9gemma-4-26B-A4B-it-GGUFJul 17, 20261.2M
- 10Qwen3.5-4B-GGUFMar 2, 20261.2M
Recently updated
- 1Qwen3.8-27B-GGUFAug 20, 20266.7M
- 2Qwen3.8-27B-NVFP4Aug 17, 20261.3M
- 3Qwen3.8-27BAug 14, 2026150.3K
- 4Qwen3.8-27B-FP8Aug 14, 202634K
- 5MiniMax-H3-FP8Aug 14, 20260
- 6MiniMax-H3-GGUFAug 14, 2026305.5K
- 7DeepSeek-V4-Pro-0813-GGUFAug 14, 202643.5K
- 8Qwen3.8-2.4T-A95B-GGUFAug 13, 202619.4K
- 9NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFAug 13, 2026112.3K
- 10LFM2.5-VL-3B-GGUFAug 12, 202611.5K
All models
| Model | DL 30D | 7D |
|---|---|---|
| gemma-4-26B-A4B-it-qat-q4_0-unquantizedunsloth/gemma-4-26b-a4b-it-qat-q4_0-unquantized | 1,880 | — |
| SmolLM2-135M-Instruct-bnb-4bitunsloth/smollm2-135m-instruct-bnb-4bit | 1,874 | — |
| gemma-3-12b-it-qat-bnb-4bitunsloth/gemma-3-12b-it-qat-bnb-4bit | 1,871 | — |
| gemma-3-12b-it-qat-int4-GGUFunsloth/gemma-3-12b-it-qat-int4-gguf | 1,870 | — |
| embeddinggemma-300m-qat-q8_0-unquantizedunsloth/embeddinggemma-300m-qat-q8_0-unquantized | 1,865 | — |
| Llama-4-Maverick-17B-128E-Instructunsloth/llama-4-maverick-17b-128e-instruct | 1,857 | — |
| Kimi-K3unsloth/kimi-k3 | 1,853 | — |
| Qwen3-VL-4B-Instruct-bnb-4bitunsloth/qwen3-vl-4b-instruct-bnb-4bit | 1,825 | — |
| Qwen3-235B-A22B-128K-GGUFunsloth/qwen3-235b-a22b-128k-gguf | 1,817 | — |
| gemma-3n-E2B-itunsloth/gemma-3n-e2b-it | 1,815 | — |
| granite-4.0-h-350m-GGUFunsloth/granite-4.0-h-350m-gguf | 1,811 | — |
| Magistral-Small-2506-GGUFunsloth/magistral-small-2506-gguf | 1,799 | — |
| gemma-3-270m-unsloth-bnb-4bitunsloth/gemma-3-270m-unsloth-bnb-4bit | 1,787 | — |
| Qwen3-4B-128K-GGUFunsloth/qwen3-4b-128k-gguf | 1,782 | — |
| Qwen2.5-Coder-3B-Instruct-GGUFunsloth/qwen2.5-coder-3b-instruct-gguf | 1,775 | — |
| Qwen3-1.7B-Baseunsloth/qwen3-1.7b-base | 1,771 | — |
| Qwen3-32B-unsloth-bnb-4bitunsloth/qwen3-32b-unsloth-bnb-4bit | 1,768 | — |
| Qwen2.5-3B-bnb-4bitunsloth/qwen2.5-3b-bnb-4bit | 1,762 | — |
| Qwen3-VL-4B-Thinking-1M-GGUFunsloth/qwen3-vl-4b-thinking-1m-gguf | 1,761 | — |
| Llama-3_1-Nemotron-Ultra-253B-v1-GGUFunsloth/llama-3_1-nemotron-ultra-253b-v1-gguf | 1,760 | — |
| DeepSeek-R1-Distill-Llama-8Bunsloth/deepseek-r1-distill-llama-8b | 1,755 | — |
| gemma-4-E2B-it-UD-MLX-4bitunsloth/gemma-4-e2b-it-ud-mlx-4bit | 1,739 | — |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4unsloth/nvidia-nemotron-3-super-120b-a12b-nvfp4 | 1,728 | — |
| LFM2.5-VL-3Bunsloth/lfm2.5-vl-3b | 1,717 | — |
| LFM2.5-8B-A1Bunsloth/lfm2.5-8b-a1b | 1,716 | — |