justinjja
/

Qwen3-235B-A22B-INT4-W4A16

Text Generation

compressed-tensors

Model card Files Files and versions

Resources

View closed (0)

How about int8 quantization?

#3 opened 6 months ago by

INT 8

#2 opened 6 months ago by

Slow inference on vLLM

#1 opened 7 months ago by