Qwen
/

Qwen3.5-122B-A10B-GPTQ-Int4

Image-Text-to-Text

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

fix chat template to avoid empty historical `<think>` blocks

#3 opened 14 days ago by

latent-variable

vLLM does not need --quantization moe_wna16

#2 opened about 1 month ago by

Does this version still have the issue of extra spaces in Chinese environments?

#1 opened about 2 months ago by