OpenModelStats

amd AI Models

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

Tracked models
204
Downloads 30D
831.5K
Total downloads
6.9M
Total likes
913
Gained 7D
241.7K

Most downloaded

  1. 1DeepSeek-R1-MXFP4Apr 13, 2026257.4K
  2. 2MiniMax-M3-MXFP4Jul 17, 202683.7K
  3. 3Kimi-K2.5-MXFP4Jul 1, 202666.3K
  4. 4GLM-5.2-MXFP4Jun 18, 202648.7K
  5. 5Qwen3.8-27B-Quark-AWQ-INT4-W4A16Aug 28, 202645K
  6. 6Qwen3.8-27B-Quark-AWQ-MXFP4Aug 26, 202644.1K
  7. 7Qwen3.8-2.4T-A95B-Quark-MXFP4Aug 14, 202623.3K
  8. 8GLM-5.3-Flash-Quark-MXFP4Sep 2, 202622K
  9. 9Llama-3.3-70B-Instruct-FP8-KVJul 1, 202517.7K
  10. 10GLM-5.3-Quark-MXFP4-AttnFP8Sep 2, 202617.2K

Fastest growing

  1. 1DeepSeek-R1-MXFP4+87.8K in 7D257.4K
  2. 2MiniMax-M3-MXFP4+24.2K in 7D83.7K
  3. 3Qwen3.8-27B-Quark-AWQ-MXFP4+22.6K in 7D44.1K
  4. 4Kimi-K2.5-MXFP4+19.9K in 7D66.3K
  5. 5Qwen3.8-27B-Quark-AWQ-INT4-W4A16+15.7K in 7D45K
  6. 6GLM-5.2-MXFP4+14K in 7D48.7K
  7. 7Qwen3.8-2.4T-A95B-Quark-MXFP4+6,886 in 7D23.3K
  8. 8Llama-3.3-70B-Instruct-FP8-KV+5,846 in 7D17.7K
  9. 9Qwen3.5-397B-A17B-MXFP4+5,034 in 7D15.1K
  10. 10DeepSeek-R1-0528-MXFP4+3,723 in 7D6,588

Recently updated

  1. 1DeepSeek-V4.1-Flash-Quark-PTPC-FP8Oct 9, 20264
  2. 2Qwen2.5-Coder-14B-Instruct_gpuep_1.0_gpu_128Oct 6, 20260
  3. 3Gemma3-4B-it_gpuep_1.0_gpu_128Oct 6, 20260
  4. 4Qwen3.6-27B_gpuep_1.0_gpu_128Oct 6, 202619
  5. 5Qwen3.6-35B-A3B_gpuep_1.0_gpu_128Oct 6, 202622
  6. 6Qwen3.5-9B_gpuep_1.0_gpu_128Oct 6, 202627
  7. 7Qwen3.5-35B-A3B_gpuep_1.0_gpu_128Oct 6, 202620
  8. 8Gemma-4-26B-A4B-it_gpuep_1.0_gpu_128Oct 6, 20260
  9. 9gpt-oss-120b-w-uint4-pergroup-asym-awq-fp16-ssln-fp32-onnxOct 6, 20260
  10. 10GPT-OSS-120B_gpuep_1.0_gpu_128Oct 6, 20260

All models

All tracked models published by amd
ModelDL 30D7D
GLM-5.1-NVFP4amd/glm-5.1-nvfp4179+0
HyLo-Llama-8MLA8GDN-64K-SFTamd/hylo-llama-8mla8gdn-64k-sft166+58
granite-4.0-h-tiny-w8a8-llmcompressoramd/granite-4.0-h-tiny-w8a8-llmcompressor161—
Llama-2-70b-chat-hf_FP8_MLPerf_V2amd/llama-2-70b-chat-hf_fp8_mlperf_v2150+32
MiniMax-M3-EAGLE3.1amd/minimax-m3-eagle3.1143+0
Kimi-K2-Thinking-MXFP4-AttnFP8amd/kimi-k2-thinking-mxfp4-attnfp8126+42
Qwen3.8-27B-fp16-ve-fp16-int4-k_quant-gs128-text-onnxamd/qwen3.8-27b-fp16-ve-fp16-int4-k_quant-gs128-text-onnx125+26
granite-4.0-h-small-w4a16-llmcompressoramd/granite-4.0-h-small-w4a16-llmcompressor106—
granite-4.0-h-small-w8a8-llmcompressoramd/granite-4.0-h-small-w8a8-llmcompressor104—
GLM-5-NVFP4amd/glm-5-nvfp4102+0
GLM-5.2-Quark-MXFP4-AttnFP8amd/glm-5.2-quark-mxfp4-attnfp8101+24
Kimi-K2.5-MXFP4-AttnFP8amd/kimi-k2.5-mxfp4-attnfp896+28
Llama-3.2-90B-Vision-Instruct-FP8-KVamd/llama-3.2-90b-vision-instruct-fp8-kv87—
HyLo-Llama-4MLA12GDN-64K-SFTamd/hylo-llama-4mla12gdn-64k-sft84+30
Qwen-2.5_1.5B_Instruct-onnx-ryzenai-npuamd/qwen-2.5_1.5b_instruct-onnx-ryzenai-npu71+0
Kimi-K2.6-NVFP4amd/kimi-k2.6-nvfp468—
DeepSeek-V4-Flash-EXTENSORamd/deepseek-v4-flash-extensor65+4
HyLo-Llama-6MLA22GDN-8K-SFTamd/hylo-llama-6mla22gdn-8k-sft65+23
granite-4.0-h-tiny-w4a16-llmcompressoramd/granite-4.0-h-tiny-w4a16-llmcompressor61—
HyLo-Llama-8MLA8GDN-8K-SFTamd/hylo-llama-8mla8gdn-8k-sft48+0
HyLo-Qwen-14MLA14GDN-8K-SFTamd/hylo-qwen-14mla14gdn-8k-sft44+0
HyLo-Llama-4MLA12GDN-8K-SFTamd/hylo-llama-4mla12gdn-8k-sft42+0
HyLo-Qwen-14MLA14M2-8K-SFTamd/hylo-qwen-14mla14m2-8k-sft42+0
HyLo-Qwen-14MLA14M2-64K-SFTamd/hylo-qwen-14mla14m2-64k-sft38+0
HyLo-Qwen-14MLA14GDN-64K-SFTamd/hylo-qwen-14mla14gdn-64k-sft38+0