hugpadhugpad

Intel / Qwen3-Omni-30B-A3B-Instruct-int4-AutoRound

Other9.4B2.6K5Updated Apr 16, 2026
Hugging Face

Downloads

2.6K

Likes

5

Last updated

Apr 16, 2026

License

apache-2.0

This model is a mixed int4 model with groupsize 128 and symmetric quantization of Qwen/Qwen3-Omni-30B-A3B-Instruct generated by intel/auto-round. Please follow the license of the original model.

Tags

  • qwen3_omni_moe
  • Any-to-Any
  • 4-bit
  • auto-round

Technical specifications

Parameters9.4B
LibraryNot available
LanguagesNot available
Base modelQwen/Qwen3-Omni-30B-A3B-Instruct
Licenseapache-2.0