nvidia
/

Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text

Model Optimizer

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

4*5090 run nvidia/Qwen3.8-Flash-Next-NVFP4

#9 opened 17 days ago by

NEXTN draft acceptance collapses to 1.5: mtp.* fp8 experts are built unquantized

#8 opened 21 days ago by

[FIX] SGLang ple_embedding_dtype fp8

#7 opened 21 days ago by

Upload avatar.png

#6 opened 21 days ago by deleted

Quant requests?

#5 opened about 1 month ago by

pathosethoslogos

Doesn't fit Spark

#4 opened about 1 month ago by

Any person have a typo problem running qwen3.8 flash next on vllm or sglang?

#3 opened about 1 month ago by

Fails to run on RTX Pro 6000

#2 opened about 1 month ago by

Any chance for a GGUF version?

#1 opened about 1 month ago by