Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Ask HN: MacBook vs. Dedicated GPU for LLM. Parent comment
With the model using MLX the speed increase is night and day. Even non-MLX is good.
You also don't have the transfer costs related to moving CPU data into the GPU.
There are no comments on this comment yet.
With the model using MLX the speed increase is night and day. Even non-MLX is good.
You also don't have the transfer costs related to moving CPU data into the GPU.