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, 20261.6M
  3. 3Llama-3.2-1B-Instruct-FP8-dynamicOct 9, 2024667.7K
  4. 4gemma-4-26B-A4B-it-FP8-dynamicAug 13, 2026551.2K
  5. 5Qwen3-Coder-Next-FP8-dynamicFeb 27, 2026402K
  6. 6gemma-4-26B-A4B-it-NVFP4Aug 13, 2026391.3K
  7. 7Llama-3.2-1B-Instruct-FP8Aug 14, 2026374.2K
  8. 8Qwen2.5-1.5B-quantized.w8a8Dec 3, 2024362.5K
  9. 9gemma-3-27b-it-quantized.w4a16Jun 9, 2025345.4K
  10. 10gemma-4-12B-it-FP8-DynamicAug 13, 2026313.1K

Recently updated

  1. 1Qwen3.8-2.4T-A95B-NVFP4-REAP-25Aug 23, 2026845
  2. 2Qwen3.8-2.4T-A95B-NVFP4-REAP-50Aug 23, 20260
  3. 3Qwen3.8-2.4T-A95B-NVFP4Aug 23, 2026843
  4. 4Qwen3-4B-speculator.dsparkAug 23, 202629
  5. 5Qwen3-4B-speculator.dflash2Aug 22, 20260
  6. 6GLM-5.2-MXFP4xMXFP8Aug 22, 2026396
  7. 7GLM-5.2-NVFP4-FP8Aug 20, 202613.8K
  8. 8Kimi-K3-NVFP4Aug 20, 202616.3K
  9. 9Hy3-NVFP4-FP8Aug 20, 20262,991
  10. 10Qwen3.8-2.4T-A95B-NVFP4-FP8Aug 20, 2026238

All models

All tracked models published by RedHatAI
ModelDL 30D7D
Qwen3.5-122B-A10B-NVFP4redhatai/qwen3.5-122b-a10b-nvfp475.3K—
Qwen2.5-VL-3B-Instruct-quantized.w8a8redhatai/qwen2.5-vl-3b-instruct-quantized.w8a869.6K—
Qwen3-8B-speculator.eagle3redhatai/qwen3-8b-speculator.eagle360.9K—
Qwen2.5-32B-Instruct-FP8-dynamicredhatai/qwen2.5-32b-instruct-fp8-dynamic59.1K—
Qwen3-32B-speculator.eagle3redhatai/qwen3-32b-speculator.eagle355.4K—
granite-3.1-2b-instruct-quantized.w4a16redhatai/granite-3.1-2b-instruct-quantized.w4a1655.2K—
Llama-3.2-1B-quantized.w8a8redhatai/llama-3.2-1b-quantized.w8a853.2K—
Qwen3-32B-FP8-dynamicredhatai/qwen3-32b-fp8-dynamic51.7K—
DeepSeek-R1-Distill-Qwen-32B-FP8-dynamicredhatai/deepseek-r1-distill-qwen-32b-fp8-dynamic43.8K—
Qwen3.8-27B-INT4redhatai/qwen3.8-27b-int443K—
Muse-Glimmer-30B-FP8-blockredhatai/muse-glimmer-30b-fp8-block41.6K—
Meta-Llama-3.1-8B-Instruct-FP8-dynamicredhatai/meta-llama-3.1-8b-instruct-fp8-dynamic41.3K—
DeepSeek-V2.5-1210-FP8redhatai/deepseek-v2.5-1210-fp837.4K—
Qwen2.5-VL-3B-Instruct-FP8-dynamicredhatai/qwen2.5-vl-3b-instruct-fp8-dynamic36.6K—
Qwen3.5-9B-quantized.w8a8redhatai/qwen3.5-9b-quantized.w8a833.4K—
Qwen3-8B-FP8-dynamicredhatai/qwen3-8b-fp8-dynamic31.9K—
Qwen3.5-35B-A3B-FP8-dynamicredhatai/qwen3.5-35b-a3b-fp8-dynamic29.2K—
Qwen3-Next-80B-A3B-Instruct-quantized.w4a16redhatai/qwen3-next-80b-a3b-instruct-quantized.w4a1628.2K—
Meta-Llama-3.1-8B-Instruct-quantized.w8a8redhatai/meta-llama-3.1-8b-instruct-quantized.w8a827.9K—
Qwen2-1.5B-Instruct-FP8redhatai/qwen2-1.5b-instruct-fp827.7K—
diffusiongemma-26B-A4B-it-FP8-dynamicredhatai/diffusiongemma-26b-a4b-it-fp8-dynamic25.8K—
Llama-3.2-1B-FP8redhatai/llama-3.2-1b-fp824.3K—
Llama-3.2-1B-Instruct-quantized.w8a8redhatai/llama-3.2-1b-instruct-quantized.w8a823K—
Kimi-K2.6-FP8-BLOCKredhatai/kimi-k2.6-fp8-block22.8K—
Qwen3-8B-quantized.w4a16redhatai/qwen3-8b-quantized.w4a1622.1K—