OpenModelStats

RedHatAI AI Models

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

Tracked models
282
Downloads 30D
8.9M
Total downloads
120.9M
Total likes
2,311
Gained 7D
2.4M

Most downloaded

  1. 1Qwen3.6-35B-A3B-NVFP4Aug 13, 20261M
  2. 2NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8Sep 17, 2026950.3K
  3. 3gemma-4-26B-A4B-it-FP8-dynamicAug 13, 2026890.2K
  4. 4Qwen3.8-27B-INT4Sep 28, 2026569.9K
  5. 5Llama-3.2-3B-Instruct-FP8-dynamicOct 9, 2024518.2K
  6. 6gemma-4-31B-it-FP8-blockAug 13, 2026433K
  7. 7Qwen3-32B-NVFP4Nov 21, 2025411.8K
  8. 8gemma-4-26B-A4B-it-NVFP4Aug 13, 2026315.2K
  9. 9gemma-3-27b-it-quantized.w4a16Jun 9, 2025293.7K
  10. 10Qwen3-Coder-Next-FP8-dynamicFeb 27, 2026288.1K

Fastest growing

  1. 1Qwen3.6-35B-A3B-NVFP4+314.9K in 7D1M
  2. 2NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8+238.5K in 7D950.3K
  3. 3gemma-4-26B-A4B-it-FP8-dynamic+218K in 7D890.2K
  4. 4Qwen3-Coder-Next-FP8-dynamic+162.9K in 7D288.1K
  5. 5Llama-3.2-3B-Instruct-FP8-dynamic+127.5K in 7D518.2K
  6. 6gemma-4-31B-it-FP8-block+118.7K in 7D433K
  7. 7Qwen3.8-27B-INT4+117.4K in 7D569.9K
  8. 8Qwen3-32B-NVFP4+106.3K in 7D411.8K
  9. 9Llama-3.2-3B-Instruct-FP8+94.2K in 7D184.9K
  10. 10gemma-3-27b-it-quantized.w4a16+88.9K in 7D293.7K

Recently updated

  1. 1Qwen3.8-27B-MXFP4Oct 8, 2026853
  2. 2gemma-4-31B-it-speculator.dflashOct 7, 2026646
  3. 3Qwen3.5-35B-A3B-quantized.w8a8Oct 6, 2026406
  4. 4Laguna-S-2.1-NVFP4Oct 6, 2026316
  5. 5Laguna-S-2.1-FP8Oct 6, 2026193
  6. 6Qwen3.8-Flash-Next-NVFP4Oct 5, 20261,503
  7. 7wolf-defender-prompt-injectionOct 5, 202687
  8. 8DeepSeek-V4-Flash-0731-NVFP4Oct 2, 2026625
  9. 9granite-3.2-2b-instructOct 1, 2026309
  10. 10Qwen3.8-27B-NVFP4Sep 30, 202634.5K

All models

All tracked models published by RedHatAI
ModelDL 30D7D
gemma-3-27b-it-FP8-dynamicredhatai/gemma-3-27b-it-fp8-dynamic57.6K+9,068
Qwen3.5-9B-quantized.w8a8redhatai/qwen3.5-9b-quantized.w8a855.7K+380
GLM-5.3-Flash-NVFP4redhatai/glm-5.3-flash-nvfp455.1K+13.6K
gemma-4-31B-it-NVFP4redhatai/gemma-4-31b-it-nvfp451.5K+24.1K
Meta-Llama-3.1-8B-Instruct-quantized.w4a16redhatai/meta-llama-3.1-8b-instruct-quantized.w4a1648.2K+11.5K
diffusiongemma-26B-A4B-it-FP8-dynamicredhatai/diffusiongemma-26b-a4b-it-fp8-dynamic47.2K+25.5K
diffusiongemma-26B-A4B-it-NVFP4redhatai/diffusiongemma-26b-a4b-it-nvfp445.4K+22.3K
Qwen3.5-9B-FP8-dynamicredhatai/qwen3.5-9b-fp8-dynamic44K+5,415
granite-3.1-2b-instruct-quantized.w4a16redhatai/granite-3.1-2b-instruct-quantized.w4a1643.6K+2,811
Qwen3.8-27B-NVFP4redhatai/qwen3.8-27b-nvfp440.7K—
Qwen3-Coder-Next-NVFP4redhatai/qwen3-coder-next-nvfp437.6K+32.6K
gemma-4-12B-it-NVFP4redhatai/gemma-4-12b-it-nvfp429.9K+20.8K
Llama-3.2-1B-quantized.w8a8redhatai/llama-3.2-1b-quantized.w8a827.6K+7,711
Qwen2.5-VL-3B-Instruct-quantized.w8a8redhatai/qwen2.5-vl-3b-instruct-quantized.w8a827.1K+7,046
Qwen2.5-VL-7B-Instruct-FP8-Dynamicredhatai/qwen2.5-vl-7b-instruct-fp8-dynamic26.5K+5,989
Llama-4-Scout-17B-16E-Instruct-quantized.w4a16redhatai/llama-4-scout-17b-16e-instruct-quantized.w4a1623.1K+375
Qwen2.5-14B-Instruct-FP8-dynamicredhatai/qwen2.5-14b-instruct-fp8-dynamic21.7K+729
Qwen3.5-4B-FP8-dynamicredhatai/qwen3.5-4b-fp8-dynamic20.3K+3,508
DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16redhatai/deepseek-r1-distill-qwen-32b-quantized.w4a1617.9K+5,588
Meta-Llama-3.1-8B-Instruct-FP8-dynamicredhatai/meta-llama-3.1-8b-instruct-fp8-dynamic17.1K+4,066
Ministral-3-14B-Instruct-2512-FP8-dynamicredhatai/ministral-3-14b-instruct-2512-fp8-dynamic16.2K+949
Qwen3-8B-speculator.eagle3redhatai/qwen3-8b-speculator.eagle315.7K+3,357
Qwen3-8B-quantized.w4a16redhatai/qwen3-8b-quantized.w4a1614.8K+1,321
Llama-3.3-70B-Instruct-NVFP4redhatai/llama-3.3-70b-instruct-nvfp414.5K+2,924
Llama-3.2-3B-quantized.w8a8redhatai/llama-3.2-3b-quantized.w8a814.3K+4,791