unsloth AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 882
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 60.4M
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 519.4M
- Total likes
- 62.2K
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- 16.6M
Most downloaded
- 1Qwen3.8-27B-GGUFAug 20, 20266.6M
- 2Qwen3-Coder-30B-A3B-Instruct-GGUFJan 30, 20266.5M
- 3Qwen3.8-27B-NVFP4Sep 8, 20262.2M
- 4MiniMax-H3-GGUFAug 14, 20261.7M
- 5gemma-4-12b-it-GGUFJul 17, 20261.6M
- 6Qwen3.8-Flash-Next-GGUFOct 6, 20261.3M
- 7Qwen3.6-35B-A3B-GGUFApr 20, 20261.3M
- 8Qwen3.5-9B-GGUFMar 2, 20261.2M
- 9Qwen3.5-4B-GGUFMar 2, 20261.1M
- 10GLM-5.3-Flash-GGUFOct 5, 20261.1M
Fastest growing
- 1Qwen3-Coder-30B-A3B-Instruct-GGUF+2.9M in 7D6.5M
- 2Qwen3.8-27B-GGUF+1.8M in 7D6.6M
- 3Qwen3.8-27B-NVFP4+767.7K in 7D2.2M
- 4gemma-4-12b-it-GGUF+544.1K in 7D1.6M
- 5Qwen3.8-Flash-Next-GGUF+376.3K in 7D1.3M
- 6MiniMax-H3-GGUF+354.6K in 7D1.7M
- 7Qwen3.5-9B-GGUF+305.3K in 7D1.2M
- 8Qwen3.6-35B-A3B-GGUF+301.1K in 7D1.3M
- 9Qwen3.6-27B-NVFP4+292.9K in 7D942.2K
- 10Qwen3.6-35B-A3B-MTP-GGUF+261K in 7D1M
Recently updated
- 1embeddinggemma-2-GGUFOct 7, 202611.5K
- 2embeddinggemma-2Oct 6, 2026622
- 3Qwen3.8-Flash-Next-GGUFOct 6, 20261.3M
- 4GLM-5.3-Flash-GGUFOct 5, 20261.1M
- 5Z-Image-Turbo-FP8Oct 5, 2026273
- 6Qwen-Image-FP8Oct 5, 202692
- 7Qwen-Image-2512-FP8Oct 5, 20260
- 8MiniMax-H3-FP8Oct 5, 20260
- 9Lumina-Image-2.0-FP8Oct 5, 20260
- 10LTX-2.3-FP8Oct 5, 20260
All models
| Model | DL 30D | 7D |
|---|---|---|
| MiniMax-M3unsloth/minimax-m3 | 68 | +12 |
| Llama-3.3-70B-Instruct-FP8-Blockunsloth/llama-3.3-70b-instruct-fp8-block | 58 | +0 |
| HiDream-I1-Fastunsloth/hidream-i1-fast | 55 | +14 |
| yi-34b-bnb-4bitunsloth/yi-34b-bnb-4bit | 52 | — |
| Apertus-70B-Instruct-2509-unsloth-bnb-4bitunsloth/apertus-70b-instruct-2509-unsloth-bnb-4bit | 50 | +17 |
| Qwen3-VL-32B-Thinking-bnb-4bitunsloth/qwen3-vl-32b-thinking-bnb-4bit | 47 | +11 |
| CrisperWhisperunsloth/crisperwhisper | 40 | +10 |
| Nemotron-3-Nano-30B-A3B-Baseunsloth/nemotron-3-nano-30b-a3b-base | 39 | — |
| Qwen3-235B-A22B-FP8unsloth/qwen3-235b-a22b-fp8 | 36 | +0 |
| FLUX.1-schnell-FP8unsloth/flux.1-schnell-fp8 | 0 | +0 |
| Qwen-Image-FP8unsloth/qwen-image-fp8 | 0 | +0 |
| MiniMax-H3-FP8unsloth/minimax-h3-fp8 | 0 | +0 |
| Z-Image-Turbo-FP8unsloth/z-image-turbo-fp8 | 0 | +0 |
| Krea-2-Turbo-FP8unsloth/krea-2-turbo-fp8 | 0 | +0 |