Will this model work with an AutoRound-quantized Qwen 3.5 9B model in the vLLM inference engine?

#1
by Vishva007 - opened

Hi,

I would like to check whether this model is compatible with an AutoRound-quantized Qwen 3.5 9B model when using the vLLM inference engine.

I am currently using (my quantized model):
Vishva007/Qwen3.5-9B-W4A16-AutoRound

Also, I understand that vLLM v0.18.0 has introduced support for Qwen 3.5 models. Could you please confirm if this setup will work correctly, or if any additional configuration or changes are required?

Thanks in advance!

Sign up or log in to comment