Re:ChatGPT's 1-Year Anniversary: Are Open-Source Large Langu...
by tarruda on Friday December 01, 2023 @06:09AM
(#38485476)
The main focus of llama.cpp has been Apple silicon, so I suspect M1 would be more efficient. The author recently published some benchmarks: https://github.com/ggerganov/llama.cpp/discussions/4167
[ Parent
| on HN ]
There are no comments on this comment yet.