nvidia
/

Cosmos3-Super

sglang-diffusion

text, image, video, audio, and action generation

Model card Files Files and versions

NVFP4 Quant

#14

by tuanlai001 - opened 8 days ago

The BF16 model weights are about 128GB. I wonder if NVFP4 quantization can fit on an RTX PRO 6000 Blackwell.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment