Re:Mistral: Our first AI endpoints are available in early ac...
by kaliqt on Monday December 11, 2023 @09:38AM
(#38601004)
Well the 4090 is certainly less efficient on this. They are using H100's or better no doubt. If they optimize for TPUs, it'll be even better.
[ Parent
| on HN ]
There are no comments on this comment yet.