hugpadhugpad

amd / Qwen3.8-27B-Quark-AWQ-INT4-W4A16

Vision6.5B4.3K23Updated Aug 28, 2026
Hugging Face

Downloads

4.3K

Likes

23

Last updated

Aug 28, 2026

License

apache-2.0

INT4 weight-only (W4A16) quantized version of Qwen/Qwen3.8-27B, produced with the AWQ algorithm using AMD Quark.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • quark
  • amd
  • quantization

Technical specifications

Parameters6.5B
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0