Hacker News new | ask | show | jobs
by mfa1999 75 days ago
How does this compare to llama.cpp in terms of performance?
1 comments
solarkraft 75 days ago
MLX is a bit faster (low double digit percentage), but uses a bit more RAM. Worthwhile tradeoff for many.
link
ysleepy 75 days ago
On my M4 Pro MLX has almost 2x tok/s
link