hugpadhugpad

kaitchup / Qwen3-VL-2B-Instruct-W4A16

Other907M2352Updated Nov 5, 2025
Hugging Face

Downloads

235

Likes

2

Last updated

Nov 5, 2025

License

apache-2.0

This is Qwen/Qwen3-VL-8B-Instruct quantized with AutoRound in W4A16 (GPTQ format). The model has been created, tested, and evaluated by The Kaitchup. The model is NOT compatible with vLLM (as of v0.11).

Tags

  • qwen3_vl
  • autoround
  • nvfp4
  • 4-bit
  • auto-round

Technical specifications

Parameters907M
LibraryNot available
LanguagesNot available
Base modelQwen/Qwen3-VL-2B-Instruct
Licenseapache-2.0