logoalt Hacker News

mfa1999 • today at 5:41 AM • 1 reply • view on HN

How does this compare to llama.cpp in terms of performance?

Replies

solarkraft • today at 6:23 AM

MLX is a bit faster (low double digit percentage), but uses a bit more RAM. Worthwhile tradeoff for many.

➕ show 1 reply