OpenModelStats

RedHatAI AI Models

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

Tracked models
214
Downloads 30D
11M
Total downloads
107.8M
Total likes
1,932
Gained 7D
—

Most downloaded

  1. 1Qwen3.6-35B-A3B-NVFP4Aug 13, 20261.6M
  2. 2gemma-4-31B-it-FP8-blockAug 13, 20261.5M
  3. 3Llama-3.2-1B-Instruct-FP8-dynamicOct 9, 2024653.1K
  4. 4gemma-4-26B-A4B-it-FP8-dynamicAug 13, 2026581.4K
  5. 5Llama-3.2-1B-Instruct-FP8Aug 14, 2026364.9K
  6. 6Qwen3-Coder-Next-FP8-dynamicFeb 27, 2026361.7K
  7. 7gemma-4-26B-A4B-it-NVFP4Aug 13, 2026357.6K
  8. 8Qwen2.5-1.5B-quantized.w8a8Dec 3, 2024355.3K
  9. 9gemma-3-27b-it-quantized.w4a16Jun 9, 2025344.4K
  10. 10Qwen3.5-9B-FP8-dynamicMay 11, 2026343.8K

Recently updated

  1. 1Qwen3.8-2.4T-A95B-NVFP4-REAP-25Aug 23, 20261,124
  2. 2Qwen3.8-2.4T-A95B-NVFP4-REAP-50Aug 23, 20260
  3. 3Qwen3.8-2.4T-A95B-NVFP4Aug 23, 20261,029
  4. 4Qwen3-4B-speculator.dsparkAug 23, 202629
  5. 5Qwen3-4B-speculator.dflash2Aug 22, 202632
  6. 6GLM-5.2-MXFP4xMXFP8Aug 22, 2026476
  7. 7GLM-5.2-NVFP4-FP8Aug 20, 202613.1K
  8. 8Kimi-K3-NVFP4Aug 20, 202616.3K
  9. 9Hy3-NVFP4-FP8Aug 20, 20263,036
  10. 10Qwen3.8-2.4T-A95B-NVFP4-FP8Aug 20, 2026272

All models

All tracked models published by RedHatAI
ModelDL 30D7D
Qwen3-VL-32B-Instruct-FP8-dynamicredhatai/qwen3-vl-32b-instruct-fp8-dynamic3,048—
Hy3-NVFP4-FP8redhatai/hy3-nvfp4-fp83,036—
Llama-3.3-70B-Instruct-quantized.w4a16redhatai/llama-3.3-70b-instruct-quantized.w4a163,027—
Muse-Glimmer-30B-INT4redhatai/muse-glimmer-30b-int42,879—
Llama-Guard-4-12B-quantized.w4a16redhatai/llama-guard-4-12b-quantized.w4a162,853—
gemma-4-31B-it-speculator.dsparkredhatai/gemma-4-31b-it-speculator.dspark2,736—
Meta-Llama-3.1-405B-Instruct-FP8-dynamicredhatai/meta-llama-3.1-405b-instruct-fp8-dynamic2,663—
Qwen3.6-35B-A3Bredhatai/qwen3.6-35b-a3b2,622—
Kimi-K2.6-NVFP4redhatai/kimi-k2.6-nvfp42,619—
DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16redhatai/deepseek-r1-distill-qwen-32b-quantized.w4a162,515—
GLM-5.2-FP8redhatai/glm-5.2-fp82,515—
Meta-Llama-3.1-8B-Instruct-quantized.w8a16redhatai/meta-llama-3.1-8b-instruct-quantized.w8a162,508—
Meta-Llama-3.1-70B-Instruct-quantized.w8a8redhatai/meta-llama-3.1-70b-instruct-quantized.w8a82,453—
Qwen3-235B-A22B-Instruct-2507-NVFP4redhatai/qwen3-235b-a22b-instruct-2507-nvfp42,449—
gemma-3-12b-it-FP8-dynamicredhatai/gemma-3-12b-it-fp8-dynamic2,418—
Qwen3.6-35B-A3B-speculator.dsparkredhatai/qwen3.6-35b-a3b-speculator.dspark2,410—
gemma-4-12B-itredhatai/gemma-4-12b-it2,397—
llama2.c-stories110M-pruned50redhatai/llama2.c-stories110m-pruned502,314—
Llama-3.1-8B-Instructredhatai/llama-3.1-8b-instruct2,312—
whisper-large-v3-turbo-quantized.w4a16redhatai/whisper-large-v3-turbo-quantized.w4a162,280—
gemma-4-31B-it-speculator.dflashredhatai/gemma-4-31b-it-speculator.dflash2,280—
Mistral-Nemo-Instruct-2407-quantized.w4a16redhatai/mistral-nemo-instruct-2407-quantized.w4a162,245—
Qwen3-14B-NVFP4redhatai/qwen3-14b-nvfp42,161—
whisper-small-quantized.w8a8redhatai/whisper-small-quantized.w8a82,106—
Meta-Llama-3-8B-Instruct-FP8redhatai/meta-llama-3-8b-instruct-fp82,102—