alt Hacker NewsYou might want to clarify that this is more of a "Look it technically works"
Not a "I actually use this"
The difference between waiting 20 minutes to answer the prompt '1+1='
and actually using it for something useful is massive here. I wonder where this idea of running AI on CPU comes from. Was it Apple astroturfing? Was it Apple fanboys? I don't see people wasting time on non-Apple CPUs. (Although, I did do this for a 7B model)
Replies
MLX uses the GPU.
That said, I wouldn't necessarily recommend spending $20,000 on a pair of Mac Studios to run models like this. The performance won't be nearly as good as the server-class GPU hardware that hosted models run on.
Mac studio way is not "AI on CPU," as M2/M4 are complex SoC, that includes a GPU with unified memory access.
The reason Macs get recommended is the unified memory, which is usable as VRAM for the GPU. People are similarly using the AMD Strix Halo for AI which also has a similar memory architecture. Time to first token for something like '1+1=' would be seconds, and then you'd be getting ~20 tokens per second, which is absolutely plenty fast for regular use. Token/s slows down at the higher end of context, but it's absolutely still practical for a lot of usecases. Though I agree that agentic coding, especially over large projects, would likely get too slow to be practical.