hugpadhugpad

ISTA-DASLab / Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Vision861.4K554Updated Oct 19, 2026
Hugging Face

Downloads

861.4K

Likes

554

Last updated

Oct 19, 2026

License

apache-2.0

A 512-expert mixture-of-experts model with half of its experts removed, targeted at code and retaining multimodal capability. 58.4 GB against 354 GB at BF16, an effective 1.89 bits per parameter of the original transformer.

Tasks & library

  • image text to text
  • gguf

Tags

  • gguf
  • gsq
  • rco
  • quantization
  • pruning
  • expert-pruning

Technical specifications

ParametersNot available
Librarygguf
LanguagesNot available
Base modelQwen/Qwen3.8-Flash-Next
Licenseapache-2.0