OpenModelStats

mlc-ai AI Models

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

Tracked models
33
Downloads 30D
291K
Total downloads
6.6M
Total likes
57
Gained 7D
76.7K

Most downloaded

  1. 1Qwen2.5-0.5B-Instruct-q4f16_1-MLCSep 7, 202563.1K
  2. 2Qwen2.5-Coder-3B-Instruct-q4f16_1-MLCSep 7, 202537.7K
  3. 3Llama-3.2-1B-Instruct-q4f16_1-MLCSep 7, 202522.1K
  4. 4Qwen2.5-1.5B-Instruct-q4f16_1-MLCSep 7, 202519.9K
  5. 5Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLCSep 7, 202516.6K
  6. 6Qwen3-4B-q4f16_1-MLCApr 18, 202616.3K
  7. 7Llama-3.2-3B-Instruct-q4f32_1-MLCSep 7, 202513.8K
  8. 8Llama-3.2-1B-Instruct-q4f32_1-MLCSep 7, 202512.6K
  9. 9SmolLM2-135M-Instruct-q0f16-MLCSep 7, 20259,957
  10. 10Qwen3-1.7B-q4f16_1-MLCApr 18, 20269,402

Fastest growing

  1. 1Qwen2.5-0.5B-Instruct-q4f16_1-MLC+14.6K in 7D63.1K
  2. 2Qwen2.5-Coder-3B-Instruct-q4f16_1-MLC+10.7K in 7D37.7K
  3. 3Llama-3.2-3B-Instruct-q4f32_1-MLC+10K in 7D13.8K
  4. 4Qwen3-4B-q4f16_1-MLC+5,112 in 7D16.3K
  5. 5Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC+4,729 in 7D16.6K
  6. 6Qwen2.5-1.5B-Instruct-q4f16_1-MLC+4,265 in 7D19.9K
  7. 7SmolLM2-360M-Instruct-q4f16_1-MLC+3,791 in 7D8,293
  8. 8Llama-3.2-1B-Instruct-q4f16_1-MLC+3,615 in 7D22.1K
  9. 9Llama-3.2-1B-Instruct-q4f32_1-MLC+2,928 in 7D12.6K
  10. 10Qwen3-1.7B-q4f16_1-MLC+2,888 in 7D9,402

Recently updated

  1. 1gemma3-1b-it-q4f16_1-MLCApr 22, 20260
  2. 2Qwen3-4B-q4f16_1-MLCApr 18, 202616.3K
  3. 3Qwen3-1.7B-q4f16_1-MLCApr 18, 20269,402
  4. 4Qwen3-0.6B-q4f16_1-MLCApr 18, 20268,156
  5. 5Qwen3.5-0.8B-q4f16_1-MLCMar 29, 20260
  6. 6Hermes-3-Llama-3.2-3B-q4f16_1-MLCSep 7, 20251,056
  7. 7Phi-3-mini-4k-instruct-q4f16_1-MLCSep 7, 20251,499
  8. 8Qwen2.5-Coder-3B-Instruct-q4f16_1-MLCSep 7, 202537.7K
  9. 9SmolLM2-135M-Instruct-q0f16-MLCSep 7, 20259,957
  10. 10SmolLM2-360M-Instruct-q4f32_1-MLCSep 7, 20252,675

All models

All tracked models published by mlc-ai
ModelDL 30D7D
Qwen2.5-0.5B-Instruct-q4f16_1-MLCmlc-ai/qwen2.5-0.5b-instruct-q4f16_1-mlc62.2K+14.6K
Qwen2.5-Coder-3B-Instruct-q4f16_1-MLCmlc-ai/qwen2.5-coder-3b-instruct-q4f16_1-mlc36.7K+10.7K
Llama-3.2-1B-Instruct-q4f16_1-MLCmlc-ai/llama-3.2-1b-instruct-q4f16_1-mlc21.9K+3,615
Qwen2.5-1.5B-Instruct-q4f16_1-MLCmlc-ai/qwen2.5-1.5b-instruct-q4f16_1-mlc19.7K+4,265
Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLCmlc-ai/qwen2.5-coder-1.5b-instruct-q4f16_1-mlc16K+4,729
Qwen3-4B-q4f16_1-MLCmlc-ai/qwen3-4b-q4f16_1-mlc15.7K+5,112
Llama-3.2-3B-Instruct-q4f32_1-MLCmlc-ai/llama-3.2-3b-instruct-q4f32_1-mlc13.9K+10K
Llama-3.2-1B-Instruct-q4f32_1-MLCmlc-ai/llama-3.2-1b-instruct-q4f32_1-mlc12.7K+2,928
SmolLM2-135M-Instruct-q0f16-MLCmlc-ai/smollm2-135m-instruct-q0f16-mlc9,373+1,266
Qwen3-1.7B-q4f16_1-MLCmlc-ai/qwen3-1.7b-q4f16_1-mlc9,151+2,888
Llama-3.2-3B-Instruct-q4f16_1-MLCmlc-ai/llama-3.2-3b-instruct-q4f16_1-mlc8,448+1,591
SmolLM2-360M-Instruct-q4f16_1-MLCmlc-ai/smollm2-360m-instruct-q4f16_1-mlc8,202+3,791
Qwen3-0.6B-q4f16_1-MLCmlc-ai/qwen3-0.6b-q4f16_1-mlc7,917+2,141
gemma-2-2b-it-q4f16_1-MLCmlc-ai/gemma-2-2b-it-q4f16_1-mlc7,618+1,925
Phi-3.5-mini-instruct-q4f16_1-MLCmlc-ai/phi-3.5-mini-instruct-q4f16_1-mlc4,134+997
Qwen2.5-3B-Instruct-q4f16_1-MLCmlc-ai/qwen2.5-3b-instruct-q4f16_1-mlc3,495+728
snowflake-arctic-embed-s-q0f32-MLCmlc-ai/snowflake-arctic-embed-s-q0f32-mlc3,144+72
Mistral-7B-Instruct-v0.3-q4f16_1-MLCmlc-ai/mistral-7b-instruct-v0.3-q4f16_1-mlc2,914+727
Llama-3.2-3B-Instruct-q4f16_0-MLCmlc-ai/llama-3.2-3b-instruct-q4f16_0-mlc2,781+683
SmolLM2-360M-Instruct-q4f32_1-MLCmlc-ai/smollm2-360m-instruct-q4f32_1-mlc2,657—
Phi-3.5-mini-instruct-q4f16_0-MLCmlc-ai/phi-3.5-mini-instruct-q4f16_0-mlc2,630+658
Qwen2.5-0.5B-Instruct-q4f32_1-MLCmlc-ai/qwen2.5-0.5b-instruct-q4f32_1-mlc2,171+522
Mistral-7B-Instruct-v0.3-q3f16_1-MLCmlc-ai/mistral-7b-instruct-v0.3-q3f16_1-mlc1,945+508
Qwen2.5-1.5B-Instruct-q4f32_1-MLCmlc-ai/qwen2.5-1.5b-instruct-q4f32_1-mlc1,795—
gemma-2-9b-it-q4f16_1-MLCmlc-ai/gemma-2-9b-it-q4f16_1-mlc1,750+97