ospatch
/

QwQ-32B-INT8-W8A8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Resources

View closed (0)

Woks 2x slower than GGUF q8

#2 opened about 1 month ago by

Context length

#1 opened about 2 months ago by

matthew-at-qamcom