News for hackers. Stuff that matters.
Re:Ask HN: MacBook vs. Dedicated GPU for LLM by EagnaIonat on Saturday June 27, 2026 @01:43AM (#48695507)
> MacBooks with their unified memory behave like a slow GPU with enormous amount of video RAM. So you can run large smart models slowly.

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.