nvidia
/

GLM-5.3-Flash-FP4-Local

Image-Text-to-Text

Model Optimizer

8-bit precision

Model card Files Files and versions

Resources

View closed (6)

Set expandable_segments in the 2 x DGX Spark environment

#8 opened 1 day ago by

Two DGX Sparks: free memory falls by 17 to 19 GiB right after the weights load; PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True keeps it higher

#7 opened 2 days ago by