hugpadhugpad

amd / Qwen3.8-27B-Quark-AWQ-MXFP4

Vision16B40.3K41Updated Aug 26, 2026
Hugging Face

Downloads

40.3K

Likes

41

Last updated

Aug 26, 2026

License

apache-2.0

Qwen/Qwen3.8-27B quantized to MXFP4 weights + MXFP4 activations with AMD Quark, using the AWQ (Activation-aware Weight Quantization) algorithm.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • quark
  • quantized
  • mxfp4

Technical specifications

Parameters16B
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0