OpenModelStats

unsloth AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
764
Downloads 30D
68.8M
Total downloads
416.5M
Total likes
53.8K
Gained 7D
—

Most downloaded

  1. 1Qwen3-Coder-30B-A3B-Instruct-GGUFJan 30, 202612.7M
  2. 2Qwen3.8-27B-GGUFAug 20, 20267M
  3. 3Qwen3.6-27B-NVFP4Jul 12, 20263.7M
  4. 4Qwen3.6-35B-A3B-NVFP4Jul 12, 20262.6M
  5. 5Qwen3.8-27B-NVFP4Aug 17, 20261.5M
  6. 6Qwen3.5-9B-GGUFMar 2, 20261.4M
  7. 7Qwen3-30B-A3B-Thinking-2507-GGUFJul 31, 20251.3M
  8. 8Qwen3.6-35B-A3B-GGUFApr 20, 20261.2M
  9. 9gemma-4-26B-A4B-it-GGUFJul 17, 20261.2M
  10. 10Qwen3.5-4B-GGUFMar 2, 20261.1M

Recently updated

  1. 1Qwen3.8-27B-GGUFAug 20, 20267M
  2. 2Qwen3.8-27B-NVFP4Aug 17, 20261.5M
  3. 3Qwen3.8-27BAug 14, 2026170K
  4. 4Qwen3.8-27B-FP8Aug 14, 202644K
  5. 5MiniMax-H3-FP8Aug 14, 20260
  6. 6MiniMax-H3-GGUFAug 14, 2026316.5K
  7. 7DeepSeek-V4-Pro-0813-GGUFAug 14, 202650.2K
  8. 8Qwen3.8-2.4T-A95B-GGUFAug 13, 202620.3K
  9. 9NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFAug 13, 2026114.3K
  10. 10LFM2.5-VL-3B-GGUFAug 12, 202611.8K

All models

All tracked models published by unsloth
ModelDL 30D7D
Qwen3-8B-Base-bnb-4bitunsloth/qwen3-8b-base-bnb-4bit2,917—
Qwen3-Embedding-8Bunsloth/qwen3-embedding-8b2,907—
DeepSeek-R1-0528-Qwen3-8Bunsloth/deepseek-r1-0528-qwen3-8b2,902—
Olmo-3-7B-Think-GGUFunsloth/olmo-3-7b-think-gguf2,901—
Llama-OuteTTS-1.0-1Bunsloth/llama-outetts-1.0-1b2,898—
gemma-2b-it-bnb-4bitunsloth/gemma-2b-it-bnb-4bit2,858—
Llama-3.2-3B-unsloth-bnb-4bitunsloth/llama-3.2-3b-unsloth-bnb-4bit2,823—
gemma-3-270m-it-qat-GGUFunsloth/gemma-3-270m-it-qat-gguf2,798—
Qwen3.6-27B-UD-MLX-NVFP4unsloth/qwen3.6-27b-ud-mlx-nvfp42,792—
Llama-3.1-Nemotron-Nano-8B-v1-GGUFunsloth/llama-3.1-nemotron-nano-8b-v1-gguf2,783—
Phi-4-mini-instruct-bnb-4bitunsloth/phi-4-mini-instruct-bnb-4bit2,771—
Qwen2.5-3B-unsloth-bnb-4bitunsloth/qwen2.5-3b-unsloth-bnb-4bit2,765—
orpheus-3b-0.1-pretrainedunsloth/orpheus-3b-0.1-pretrained2,741—
Qwen2.5-Coder-3B-Instructunsloth/qwen2.5-coder-3b-instruct2,737—
gemma-4-12B-it-qat-q4_0-unquantizedunsloth/gemma-4-12b-it-qat-q4_0-unquantized2,729—
MiMo-V2.5-GGUFunsloth/mimo-v2.5-gguf2,728—
Krea-2-Turbounsloth/krea-2-turbo2,710—
Llama-3.1-Nemotron-Nano-8B-v1unsloth/llama-3.1-nemotron-nano-8b-v12,695—
granite-4.0-1b-GGUFunsloth/granite-4.0-1b-gguf2,680—
Qwen2-VL-7B-Instructunsloth/qwen2-vl-7b-instruct2,665—
Mistral-Nemo-Instruct-2407unsloth/mistral-nemo-instruct-24072,660—
Mistral-Small-Instruct-2409-bnb-4bitunsloth/mistral-small-instruct-2409-bnb-4bit2,660—
Qwen3-8B-128K-GGUFunsloth/qwen3-8b-128k-gguf2,644—
Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bitunsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit2,632—
Llama-3_3-Nemotron-Super-49B-v1_5-GGUFunsloth/llama-3_3-nemotron-super-49b-v1_5-gguf2,627—