Report: GPU VRAM Usage = 55GB in exl2 textgenwebui

#1
by kyleboddy - opened

Using gpu-split 16, 16, 16 on 3x RTX 3090s, 21/20/14 GB actual usage with overhead taken account of.

No action required, just notating in these for people to see VRAM usage in these quants. Thanks for these, @Dracones !

image.png

Sign up or log in to comment