sakamakismile
/

Qwen3.6-27B-NVFP4

8-bit precision

compressed-tensors

Model card Files Files and versions

Resources

View closed (1)

Home Lab Recipe on Blackwell GPU

#10 opened about 2 months ago by

I have encountered multiple instances where it automatically stops responding during the process — when called in Claudecode, Codebuddy, and Trae. Has anyone else experienced this?

#9 opened about 2 months ago by

abliterated?

#8 opened about 2 months ago by

MTP not responding

#7 opened about 2 months ago by

claude code

#6 opened about 2 months ago by

Qwen3.6-27B-NVFP4 is slower than official FP8 on Blackwell; possible fallback / FLA path mismatch on vLLM

#5 opened about 2 months ago by

sglang

#4 opened about 2 months ago by

vllm部署有问题啊

#3 opened about 2 months ago by

HOLY $#!T...

#1 opened about 2 months ago by