OpenModelStats

unsloth AI Models

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

Tracked models
882
Downloads 30D
60.4M
Total downloads
519.4M
Total likes
62.2K
Gained 7D
16.6M

Most downloaded

  1. 1Qwen3.8-27B-GGUFAug 20, 20266.6M
  2. 2Qwen3-Coder-30B-A3B-Instruct-GGUFJan 30, 20266.5M
  3. 3Qwen3.8-27B-NVFP4Sep 8, 20262.2M
  4. 4MiniMax-H3-GGUFAug 14, 20261.7M
  5. 5gemma-4-12b-it-GGUFJul 17, 20261.6M
  6. 6Qwen3.8-Flash-Next-GGUFOct 6, 20261.3M
  7. 7Qwen3.6-35B-A3B-GGUFApr 20, 20261.3M
  8. 8Qwen3.5-9B-GGUFMar 2, 20261.2M
  9. 9Qwen3.5-4B-GGUFMar 2, 20261.1M
  10. 10GLM-5.3-Flash-GGUFOct 5, 20261.1M

Fastest growing

  1. 1Qwen3-Coder-30B-A3B-Instruct-GGUF+2.9M in 7D6.5M
  2. 2Qwen3.8-27B-GGUF+1.8M in 7D6.6M
  3. 3Qwen3.8-27B-NVFP4+767.7K in 7D2.2M
  4. 4gemma-4-12b-it-GGUF+544.1K in 7D1.6M
  5. 5Qwen3.8-Flash-Next-GGUF+376.3K in 7D1.3M
  6. 6MiniMax-H3-GGUF+354.6K in 7D1.7M
  7. 7Qwen3.5-9B-GGUF+305.3K in 7D1.2M
  8. 8Qwen3.6-35B-A3B-GGUF+301.1K in 7D1.3M
  9. 9Qwen3.6-27B-NVFP4+292.9K in 7D942.2K
  10. 10Qwen3.6-35B-A3B-MTP-GGUF+261K in 7D1M

Recently updated

  1. 1embeddinggemma-2-GGUFOct 7, 202611.5K
  2. 2embeddinggemma-2Oct 6, 2026622
  3. 3Qwen3.8-Flash-Next-GGUFOct 6, 20261.3M
  4. 4GLM-5.3-Flash-GGUFOct 5, 20261.1M
  5. 5Z-Image-Turbo-FP8Oct 5, 2026273
  6. 6Qwen-Image-FP8Oct 5, 202692
  7. 7Qwen-Image-2512-FP8Oct 5, 20260
  8. 8MiniMax-H3-FP8Oct 5, 20260
  9. 9Lumina-Image-2.0-FP8Oct 5, 20260
  10. 10LTX-2.3-FP8Oct 5, 20260

All models

All tracked models published by unsloth
ModelDL 30D7D
Mistral-Large-Instruct-2407-bnb-4bitunsloth/mistral-large-instruct-2407-bnb-4bit148+29
DeepSeek-V4-Prounsloth/deepseek-v4-pro145+28
Phi-4-reasoning-plus-unsloth-bnb-4bitunsloth/phi-4-reasoning-plus-unsloth-bnb-4bit141—
whisper-baseunsloth/whisper-base131+19
Kimi-K2.6unsloth/kimi-k2.6129+35
Qwen3-Next-80B-A3B-Instructunsloth/qwen3-next-80b-a3b-instruct125+20
North-Mini-Code-1.0unsloth/north-mini-code-1.0122—
MiniMax-H3unsloth/minimax-h3121+33
Llama-4-Scout-17B-16E-Instruct-unsloth-dynamic-bnb-4bitunsloth/llama-4-scout-17b-16e-instruct-unsloth-dynamic-bnb-4bit118+37
Qwen2.5-Coder-32B-bnb-4bitunsloth/qwen2.5-coder-32b-bnb-4bit115—
aya-vision-8bunsloth/aya-vision-8b101+51
Qwen3-4B-Thinking-2507-FP8unsloth/qwen3-4b-thinking-2507-fp897+19
HiDream-I1-Fullunsloth/hidream-i1-full96+7
Llama-3.1-8B-Instruct-FP8-Blockunsloth/llama-3.1-8b-instruct-fp8-block94+0
PaddleOCR-VLunsloth/paddleocr-vl87—
CrisperWhisperunsloth/crisperwhisper86+10
Qwen3-VL-4B-Thinking-FP8unsloth/qwen3-vl-4b-thinking-fp881+8
MiniMax-M3unsloth/minimax-m368+12
HiDream-I1-Fastunsloth/hidream-i1-fast59+14
Llama-3.3-70B-Instruct-FP8-Blockunsloth/llama-3.3-70b-instruct-fp8-block58+0
Apertus-70B-Instruct-2509-unsloth-bnb-4bitunsloth/apertus-70b-instruct-2509-unsloth-bnb-4bit50+17
Qwen3-VL-32B-Thinking-bnb-4bitunsloth/qwen3-vl-32b-thinking-bnb-4bit45+11
Qwen3-235B-A22B-FP8unsloth/qwen3-235b-a22b-fp836+0
Qwen-Image-FP8unsloth/qwen-image-fp80+0
Krea-2-Turbo-FP8unsloth/krea-2-turbo-fp80+0