48.7K models tracked · refreshed 19 hours ago

Track the models shaping open-source AI

Daily download history, growth metrics and rankings for open-source AI models — built from our own observations, so you can see how a model got here, not just where it stands today.

Free to use · No account required

Models tracked
48.7K
Observations
48.7K
Publishers
14K
Last refresh
19 hours ago

Trending now

View all →
  1. 1Qwen3.8-27BQwen1,490
  2. 2Qwen3.8-27B-GGUFunsloth1,065
  3. 3Qwen3.8-27B-Uncensored-MLXorcarouter815
  4. 4Qwen3.8-27B-OBLITERATEDOBLITERATUS605
  5. 5Qwen3.8-27B-Uncensored-FP8orcarouter505
  6. 6Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFHauhauCS496
  7. 7LTX-2.5Lightricks403
  8. 8Ornith-1.5-35B-A3Bornith-ai377
  9. 9Qwen3.8-27B-Uncensored-GGUFJonathanColetti338
  10. 10MiniMax-Music3MiniMaxAI305

Most downloaded

View all →
  1. 1all-MiniLM-L6-v2sentence-transformers255.8M
  2. 2bert-base-uncasedgoogle-bert95.4M
  3. 3ms-marco-MiniLM-L6-v2cross-encoder87.6M
  4. 4bge-small-en-v1.5BAAI71.6M
  5. 5electra-base-discriminatorgoogle54.7M
  6. 6paraphrase-multilingual-MiniLM-L12-v2sentence-transformers54.5M
  7. 7bge-m3BAAI36.4M
  8. 8chronos-2amazon35.1M
  9. 9unidepth-v2-vitl14lpiccinelli26.3M
  10. 10all-mpnet-base-v2sentence-transformers24.9M

New & rising

View all →
  1. 1MiniMax-H3Comfy-Org17.8M
  2. 2Qwen3.6-35B-A3B-NVFP4nvidia12.4M
  3. 3OTel-2.0-LLM-31B-ITfarbodtavakkoli7.1M
  4. 4Qwen3.8-27B-GGUFunsloth7M
  5. 5Ornith-1.0-9B-GGUFornith-ai4.9M
  6. 6MiniMax-H3MiniMaxAI4.5M
  7. 7Ornith-1.0-35B-GGUFornith-ai3.7M
  8. 8Ornith-1.0-35Bornith-ai3.3M
  9. 9DeepSeek-V4-Flash-0731deepseek-ai3.3M
  10. 10Unlimited-OCRbaidu3.1M

Explore by task

All tasks →

Top publishers

All publishers →
  1. 1sentence-transformers369.8M
  2. 2Qwen333.6M
  3. 3BAAI169.1M
  4. 4google144M
  5. 5google-bert107.9M
  6. 6cross-encoder103.2M
  7. 7facebook74.1M
  8. 8unsloth68.8M
  9. 9openai64.1M
  10. 10Comfy-Org57.5M

What OpenModelStats tracks

Historical snapshots

Every day, OpenModelStats records what it observes about each tracked model — downloads, likes and rank positions — building a history that did not exist anywhere else.

How observation works

Growth & velocity

Interval gains are derived only from changes in cumulative counters between OpenModelStats observations. When a number cannot be calculated reliably, we show nothing at all.

How metrics are computed

Independent rankings

Rankings compare tracked models against each other and are labeled as such. Accuracy matters more than impressive-sounding numbers.

See current rankings
OpenModelStats — Open-source AI model stats, rankings & growth history