News for hackers. Stuff that matters.

A comment on Performance of llama.cpp on Apple Silicon A-series. Parent comment

Re:Performance of llama.cpp on Apple Silicon A-series by larodi on Wednesday December 20, 2023 @05:12AM (#38707076)
There’s indeed a lot of GPU time not utilised even by modern games. I can definitely imagine new games utilising llms much more even and with local inference option.
[ Parent | on HN ]

There are no comments on this comment yet.