OpenModelStats

amd AI Models

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

Tracked models
70
Downloads 30D
823.7K
Total downloads
5.5M
Total likes
703
Gained 7D
—

Most downloaded

  1. 1MiniMax-M3-MXFP4Jul 17, 2026110.5K
  2. 2GLM-5.2-MXFP4Jun 18, 2026106.6K
  3. 3DeepSeek-R1-MXFP4Apr 13, 202668.6K
  4. 4Kimi-K2.5-MXFP4Jul 1, 202661.9K
  5. 5Qwen3.8-27B-Quark-AWQ-INT4-W4A16Aug 17, 202652.5K
  6. 6Qwen3.5-397B-A17B-MXFP4Jul 16, 202636K
  7. 7DeepSeek-R1-0528-MXFP4-v2May 14, 202630.7K
  8. 8Llama-3.1-8B-Instruct-FP8-KVJun 18, 202629K
  9. 9PARD-Llama-3.2-1BJun 18, 202620.7K
  10. 10MiniMax-M2.1-MXFP4May 28, 202616.8K

Recently updated

  1. 1Instella-MoE-16B-A3B-ThinkAug 21, 20264,822
  2. 2Instella-MoE-16B-A3B-PretrainAug 21, 20262,846
  3. 3Instella-MoE-16B-A3B-BaseAug 21, 20262,715
  4. 4Qwen3.6-35B-A3B-EXTENSORAug 18, 20265,327
  5. 5gpt-oss-20b-BF16-w8a8-llmcompressor-v0.10.0.2Aug 18, 20261,961
  6. 6Qwen3.8-27B-Quark-AWQ-INT4-W4A16Aug 17, 202652.5K
  7. 7Qwen3.8-27B-Quark-AWQ-MXFP4Aug 15, 20261,705
  8. 8Qwen3.8-2.4T-A95B-Quark-MXFP4Aug 14, 20265,315
  9. 9Qwen3.6-35B-A3B-w8a8-llmcompressor-v0.12.0Aug 10, 20262,126
  10. 10gemma-4-26B-A4B-it-w8a8-llmcompressor-v0.12.0Aug 6, 2026942

All models

All tracked models published by amd
ModelDL 30D7D
MiniMax-M3-MXFP4amd/minimax-m3-mxfp4110.5K—
GLM-5.2-MXFP4amd/glm-5.2-mxfp4106.6K—
DeepSeek-R1-MXFP4amd/deepseek-r1-mxfp468.6K—
Kimi-K2.5-MXFP4amd/kimi-k2.5-mxfp461.9K—
Qwen3.8-27B-Quark-AWQ-INT4-W4A16amd/qwen3.8-27b-quark-awq-int4-w4a1652.5K—
Qwen3.5-397B-A17B-MXFP4amd/qwen3.5-397b-a17b-mxfp436K—
DeepSeek-R1-0528-MXFP4-v2amd/deepseek-r1-0528-mxfp4-v230.7K—
Llama-3.1-8B-Instruct-FP8-KVamd/llama-3.1-8b-instruct-fp8-kv29K—
PARD-Llama-3.2-1Bamd/pard-llama-3.2-1b20.7K—
MiniMax-M2.1-MXFP4amd/minimax-m2.1-mxfp416.8K—
DeepSeek-R1-MXFP4-ASQamd/deepseek-r1-mxfp4-asq16.8K—
gpt-oss-120b-w-mxfp4-a-fp8amd/gpt-oss-120b-w-mxfp4-a-fp815.9K—
Kimi-K2.6-MXFP4amd/kimi-k2.6-mxfp415.6K—
Qwen3.5-397B-A17B-MoE-MXFP4amd/qwen3.5-397b-a17b-moe-mxfp415.3K—
Llama-3.1-8B-Instruct-FP8-KV-Quark-testamd/llama-3.1-8b-instruct-fp8-kv-quark-test13.4K—
AMD-Llama-135mamd/amd-llama-135m11.3K—
gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8amd/gpt-oss-20b-moe-quant-w-mxfp4-a-fp8-kv-fp811.2K—
grok-1-W4A8KV8amd/grok-1-w4a8kv810.3K—
Llama-3.3-70B-Instruct-FP8-KVamd/llama-3.3-70b-instruct-fp8-kv9,965—
DeepSeek-R1-0528-MXFP4amd/deepseek-r1-0528-mxfp49,336—
Kimi-K2.7-Code-MXFP4amd/kimi-k2.7-code-mxfp49,206—
Qwen2.5-1.5B-Instruct-ptpc-Quark-tsamd/qwen2.5-1.5b-instruct-ptpc-quark-ts8,358—
Llama-3.1-8B-Instruct-w-int8-a-int8-sym-testamd/llama-3.1-8b-instruct-w-int8-a-int8-sym-test8,270—
Qwen3.5-35B-A3B-MXFP4amd/qwen3.5-35b-a3b-mxfp47,997—
Mixtral-8x7B-Instruct-v0.1-FP8-KVamd/mixtral-8x7b-instruct-v0.1-fp8-kv7,051—