unsloth
/

Qwen3.8-27B-NVFP4

compressed-tensors

Model card Files Files and versions

Resources

View closed (0)

Using this on vllm but excessive tbinking

#13 opened about 4 hours ago by

Changelog?

#12 opened about 10 hours ago by

Does not work with vllm 0.27.1 (latest)

#11 opened about 12 hours ago by

Tokenizer bug allows only small images

#10 opened about 17 hours ago by

thinking tags

#9 opened about 21 hours ago by

Inferact/Qwen3.8-27B-NVFP4 is on vLLM's official documentation

#8 opened 1 day ago by

pathosethoslogos

Qwen3.8-27B Serving Configs: DGX Spark vLLM NVFP4

#7 opened 1 day ago by

Why no NVFP4 GGUF?

#6 opened 1 day ago by

What is the target size for NVFP4?

#5 opened 1 day ago by

Can it be reduced much further?

#4 opened 1 day ago by

So fast and great. Thank so muchhhh.

#3 opened 1 day ago by

How ?

#2 opened 1 day ago by

Thank you

#1 opened 1 day ago by