News for hackers. Stuff that matters.

A comment on Tencent Hunyuan-Large. Parent comment

Re:Tencent Hunyuan-Large by DrPhish on Wednesday November 13, 2024 @09:50PM (#42132657)
Yes I have the same engineering sample. I can only keep 48 cores fed with max memory bandwidth given current llama.cpp architectural constraints
[ Parent | on HN ]

There are no comments on this comment yet.