nvidia
/

GLM-5-NVFP4

Text Generation

Model Optimizer

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

Tested on B300 and got roughly the same output as FP8

#4 opened 9 days ago by

SciBench Results - methodology

#3 opened 10 days ago by

Dockerfile build failed

#2 opened 13 days ago by

no lmsysorg/sglang:nightly-dev-cu13-20260305-33c92732 docker image found

#1 opened 13 days ago by