hugpadhugpad

kaitchup / Qwen3.8-27B-SLQ-EAR97.8

Text Generation24B1490Updated Oct 30, 2026
Hugging Face

Downloads

149

Likes

0

Last updated

Oct 30, 2026

License

apache-2.0

This is Qwen/Qwen3.8-27B, compressed with a customized version of SLQ (Statistically-Lossless Quantization) and packed for Humming in vLLM. The search combines integer quantization candidates and chooses precision and group size separately for individual projections.

Tasks & library

  • text generation

Tags

  • qwen3_5
  • slq
  • mixed-precision
  • humming
  • vllm
  • gptq

Technical specifications

Parameters24B
LibraryNot available
LanguagesNot available
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0