llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard

Published 20 hours ago • verified publisher icon ggml-org

CUDA: correct the lowest Maxwell supported by CUDA 12

Open PureJourney opened this issue 2 days ago • 0 comments

The the lowest architecture supported by CUDA 12 is Maxwell.
And 5.0 is the lowest one in the Maxwell family.

PureJourney avatar Feb 20 '25 21:02 PureJourney