ISTA-DASLab / Qwen3-30B-A3B-P48NVFP4-MoESQ

Text Generation20B8607Updated Oct 5, 2026

Downloads

860

Likes

7

Last updated

Oct 5, 2026

License

apache-2.0

A W4A4 + paired-4:8 sparse compressed checkpoint of Qwen/Qwen3-30B-A3B, produced with MoESQ. The MoE expert weights are NVFP4 with paired-4:8 structured sparsity. They are stored sparse: only the kept values plus a small mask are on disk, not a dense NVFP4 tensor with zeros in…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • qwen3_moe
  • text-generation
  • qwen3-moe
  • moe
  • nvfp4

Technical specifications

Parameters20B
Librarytransformers
Languagesen
Licenseapache-2.0