Qwen
/

Qwen3.5-27B-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

#8 opened 13 days ago by

latent-variable

NotImplementedError Error in gqtqmodel

#7 opened 22 days ago by

30.3 GB?

#6 opened about 1 month ago by

dense 模型量化参数也配置 moe? --quantization moe_wna16

#5 opened about 1 month ago by

会发布AWQ的量化版吗

#4 opened about 1 month ago by

Request: preview

#3 opened about 2 months ago by

facing issues with tranformers version

#2 opened about 2 months ago by

怎么和fp8一样大

#1 opened about 2 months ago by