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, 2026261.4K
  2. 2MiniMax-M3-MXFP4Jul 17, 202685.9K
  3. 3Kimi-K2.5-MXFP4Jul 1, 202665.8K
  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, 202643.5K
  7. 7Qwen3.8-2.4T-A95B-Quark-MXFP4Aug 14, 202622.9K
  8. 8GLM-5.3-Flash-Quark-MXFP4Sep 2, 202622K
  9. 9GLM-5.3-Quark-MXFP4-AttnFP8Sep 2, 202619.5K
  10. 10Llama-3.3-70B-Instruct-FP8-KVJul 1, 202517.2K

Fastest growing

  1. 1DeepSeek-R1-MXFP4+87.8K in 7D261.4K
  2. 2MiniMax-M3-MXFP4+24.2K in 7D85.9K
  3. 3Qwen3.8-27B-Quark-AWQ-MXFP4+22.6K in 7D43.5K
  4. 4Kimi-K2.5-MXFP4+19.9K in 7D65.8K
  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 7D22.9K
  8. 8Llama-3.3-70B-Instruct-FP8-KV+5,846 in 7D17.2K
  9. 9Qwen3.5-397B-A17B-MXFP4+5,034 in 7D16.7K
  10. 10gpt-oss-120b-w-mxfp4-a-fp8+3,723 in 7D11.4K

Recently updated

  1. 1Qwen2.5-Coder-14B-Instruct_gpuep_1.0_gpu_128Oct 6, 20260
  2. 2Gemma3-4B-it_gpuep_1.0_gpu_128Oct 6, 20260
  3. 3Qwen3.6-27B_gpuep_1.0_gpu_128Oct 6, 202619
  4. 4Qwen3.6-35B-A3B_gpuep_1.0_gpu_128Oct 6, 202622
  5. 5Qwen3.5-9B_gpuep_1.0_gpu_128Oct 6, 202627
  6. 6Qwen3.5-35B-A3B_gpuep_1.0_gpu_128Oct 6, 202620
  7. 7Gemma-4-26B-A4B-it_gpuep_1.0_gpu_128Oct 6, 20260
  8. 8gpt-oss-120b-w-uint4-pergroup-asym-awq-fp16-ssln-fp32-onnxOct 6, 20260
  9. 9GPT-OSS-120B_gpuep_1.0_gpu_128Oct 6, 20260
  10. 10gemma-4-e4b-it-mobius-int4_rai_1.8.0_medusa_1.0_npuOct 6, 20268

All models

All tracked models published by amd
ModelDL 30D7D
DeepSeek-R1-MXFP4amd/deepseek-r1-mxfp4280.1K+87.8K
MiniMax-M3-MXFP4amd/minimax-m3-mxfp485.9K+24.2K
Kimi-K2.5-MXFP4amd/kimi-k2.5-mxfp466.4K+19.9K
GLM-5.2-MXFP4amd/glm-5.2-mxfp447K+14K
Qwen3.8-27B-Quark-AWQ-INT4-W4A16amd/qwen3.8-27b-quark-awq-int4-w4a1645.7K+15.7K
Qwen3.8-27B-Quark-AWQ-MXFP4amd/qwen3.8-27b-quark-awq-mxfp444K+22.6K
Qwen3.8-2.4T-A95B-Quark-MXFP4amd/qwen3.8-2.4t-a95b-quark-mxfp421K+6,886
GLM-5.3-Quark-MXFP4-AttnFP8amd/glm-5.3-quark-mxfp4-attnfp819.3K+992
Qwen3.5-397B-A17B-MXFP4amd/qwen3.5-397b-a17b-mxfp419K+5,034
Llama-3.3-70B-Instruct-FP8-KVamd/llama-3.3-70b-instruct-fp8-kv16.9K+5,846
Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2amd/qwen3.5-397b-a17b-mxfp4-attnfp8-v214K+2,612
Qwen3-VL-8B-Instruct-w8a8-llmcompressoramd/qwen3-vl-8b-instruct-w8a8-llmcompressor12.5K+132
GLM-5.3-Flash-Quark-MXFP4amd/glm-5.3-flash-quark-mxfp411.3K+721
gpt-oss-120b-w-mxfp4-a-fp8amd/gpt-oss-120b-w-mxfp4-a-fp811.3K+3,723
Qwen3-VL-235B-A22B-Instruct-MXFP4amd/qwen3-vl-235b-a22b-instruct-mxfp49,760+164
Qwen3.8-Flash-Next-Quark-MXFP4amd/qwen3.8-flash-next-quark-mxfp49,200+896
DeepSeek-R1-0528-MXFP4amd/deepseek-r1-0528-mxfp48,934+3,723
grok-1-W4A8KV8amd/grok-1-w4a8kv88,758+2,327
AMD-Llama-135mamd/amd-llama-135m7,459+1,200
Kimi-K2.6-MXFP4amd/kimi-k2.6-mxfp46,817+1,169
DeepSeek-R1-0528-MXFP4-MTP-MoEFP4amd/deepseek-r1-0528-mxfp4-mtp-moefp44,826+1,295
gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8amd/gpt-oss-20b-moe-quant-w-mxfp4-a-fp8-kv-fp84,551+1,268
gpt-oss-20b-WFP8-AFP8-KVFP8amd/gpt-oss-20b-wfp8-afp8-kvfp84,453+1,214
DeepSeek-V4-Flash-MXFP4amd/deepseek-v4-flash-mxfp44,359+283
Instella-MoE-16B-A3B-Thinkamd/instella-moe-16b-a3b-think2,920+1,676