logoalt Hacker News

aromanyesterday at 8:14 PM1 replyview on HN

What would be the bottleneck?


Replies

bigyabaiyesterday at 11:22 PM

The integrated GPU. Not enough compute onboard to handle prefill for 100gb+ models, and the decode is constrained by memory bandwidth that's lower than most dGPUs that price.

Apple would be in a much stronger spot right now if they didn't pretend like eGPUs were inconceivable black magic that Macs are incompatible with.

show 1 reply