hugpadhugpad

kaitchup / Qwen3.5-27B-autoround-W4A16

Other6.8B16310Updated Feb 27, 2026
Hugging Face

Downloads

163

Likes

10

Last updated

Feb 27, 2026

License

apache-2.0

This is Qwen/Qwen3.5-27B quantized with AutoRound to W4A16 (INT). The model is compatible with vLLM (tested: v0.16.1rc1). Tested with an H200. Currently under evaluation.

Tags

  • qwen3_5
  • autoround
  • 4-bit
  • auto-round

Technical specifications

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