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, 20261.1M
  2. 2NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8Sep 17, 2026917.8K
  3. 3gemma-4-26B-A4B-it-FP8-dynamicAug 13, 2026890.8K
  4. 4Qwen3.8-27B-INT4Sep 28, 2026574.2K
  5. 5Llama-3.2-3B-Instruct-FP8-dynamicOct 9, 2024518.3K
  6. 6gemma-4-31B-it-FP8-blockAug 13, 2026424.2K
  7. 7Qwen3-32B-NVFP4Nov 21, 2025412K
  8. 8gemma-4-26B-A4B-it-NVFP4Aug 13, 2026315.6K
  9. 9gemma-3-27b-it-quantized.w4a16Jun 9, 2025305.5K
  10. 10Qwen3-Coder-Next-FP8-dynamicFeb 27, 2026288K

Fastest growing

  1. 1Qwen3.6-35B-A3B-NVFP4+314.9K in 7D1.1M
  2. 2NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8+238.5K in 7D917.8K
  3. 3gemma-4-26B-A4B-it-FP8-dynamic+218K in 7D890.8K
  4. 4Qwen3-Coder-Next-FP8-dynamic+162.9K in 7D288K
  5. 5Llama-3.2-3B-Instruct-FP8-dynamic+127.5K in 7D518.3K
  6. 6gemma-4-31B-it-FP8-block+118.7K in 7D424.2K
  7. 7Qwen3.8-27B-INT4+117.4K in 7D574.2K
  8. 8Qwen3-32B-NVFP4+106.3K in 7D412K
  9. 9Llama-3.2-3B-Instruct-FP8+94.2K in 7D184.8K
  10. 10gemma-3-27b-it-quantized.w4a16+88.9K in 7D305.5K

Recently updated

  1. 1gemma-4-31B-it-speculator.dflashOct 7, 2026618
  2. 2Qwen3.5-35B-A3B-quantized.w8a8Oct 6, 2026406
  3. 3Laguna-S-2.1-NVFP4Oct 6, 2026316
  4. 4Laguna-S-2.1-FP8Oct 6, 2026193
  5. 5Qwen3.8-Flash-Next-NVFP4Oct 5, 20261,414
  6. 6wolf-defender-prompt-injectionOct 5, 202683
  7. 7DeepSeek-V4-Flash-0731-NVFP4Oct 2, 2026605
  8. 8granite-3.2-2b-instructOct 1, 2026309
  9. 9Qwen3.8-27B-NVFP4Sep 30, 202635.3K
  10. 10Kimi-K3-INT4Sep 30, 2026115

All models

All tracked models published by RedHatAI
ModelDL 30D7D
Qwen3.6-35B-A3B-NVFP4redhatai/qwen3.6-35b-a3b-nvfp41.1M+314.9K
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8redhatai/nvidia-nemotron-3.5-lightning-30b-a3b-fp8917.8K+238.5K
gemma-4-26B-A4B-it-FP8-dynamicredhatai/gemma-4-26b-a4b-it-fp8-dynamic890.8K+218K
Qwen3.8-27B-INT4redhatai/qwen3.8-27b-int4574.2K+117.4K
Llama-3.2-3B-Instruct-FP8-dynamicredhatai/llama-3.2-3b-instruct-fp8-dynamic518.3K+127.5K
gemma-4-31B-it-FP8-blockredhatai/gemma-4-31b-it-fp8-block424.2K+118.7K
Qwen3-32B-NVFP4redhatai/qwen3-32b-nvfp4412K+106.3K
gemma-4-26B-A4B-it-NVFP4redhatai/gemma-4-26b-a4b-it-nvfp4315.6K+11.6K
gemma-3-27b-it-quantized.w4a16redhatai/gemma-3-27b-it-quantized.w4a16305.5K+88.9K
Qwen3-Coder-Next-FP8-dynamicredhatai/qwen3-coder-next-fp8-dynamic288K+162.9K
Llama-3.2-1B-Instruct-FP8-dynamicredhatai/llama-3.2-1b-instruct-fp8-dynamic238.4K+82.9K
gemma-4-31B-it-FP8-dynamicredhatai/gemma-4-31b-it-fp8-dynamic228.3K+54.5K
Llama-3.2-3B-Instruct-FP8redhatai/llama-3.2-3b-instruct-fp8184.8K+94.2K
Meta-Llama-3.1-70B-Instruct-FP8redhatai/meta-llama-3.1-70b-instruct-fp8138.8K+34K
DeepSeek-Coder-V2-Lite-Instruct-FP8redhatai/deepseek-coder-v2-lite-instruct-fp8133.5K+32.5K
Qwen2.5-1.5B-quantized.w8a8redhatai/qwen2.5-1.5b-quantized.w8a8129.3K+45.7K
Qwen3.5-122B-A10B-NVFP4redhatai/qwen3.5-122b-a10b-nvfp4127.1K+1,771
Meta-Llama-3.1-8B-Instruct-FP8redhatai/meta-llama-3.1-8b-instruct-fp8125.6K+43.5K
Llama-3.3-70B-Instruct-FP8-dynamicredhatai/llama-3.3-70b-instruct-fp8-dynamic120.3K+29.3K
Qwen2.5-32B-Instruct-FP8-dynamicredhatai/qwen2.5-32b-instruct-fp8-dynamic112.5K+36K
whisper-large-v3-FP8-dynamicredhatai/whisper-large-v3-fp8-dynamic86.7K+14.9K
gemma-4-12B-it-FP8-Dynamicredhatai/gemma-4-12b-it-fp8-dynamic78K+28.7K
Llama-3.2-1B-Instruct-FP8redhatai/llama-3.2-1b-instruct-fp864.7K+21.8K
Muse-Glimmer-30B-FP8-blockredhatai/muse-glimmer-30b-fp8-block58.4K+19.1K
gemma-3-27b-it-FP8-dynamicredhatai/gemma-3-27b-it-fp8-dynamic57.7K+9,068