hugpadhugpad

aws-prototyping / Qwen3-235B-A22B-Instruct-2507_MXFP4

Text Generation242B180Updated Jan 7, 2026
Hugging Face

Downloads

18

Likes

0

Last updated

Jan 7, 2026

License

apache-2.0

This checkpoint is a variant of Qwen3-235B-A22B-Instruct-2507, where expert weights have been quantized to MXFP4 format similarly to gpt-oss-20b and gpt-oss-120b.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • qwen3_moe
  • text-generation
  • conversational
  • 8-bit
  • mxfp4

Technical specifications

Parameters242B
Librarytransformers
LanguagesNot available
Licenseapache-2.0