For text inference, what you want is M1/M2 Ultra with its 800 Gb/s RAM. Max only... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		int_19h on Feb 23, 2024 \| parent \| context \| favorite \| on: Stable Diffusion 3 For text inference, what you want is M1/M2 Ultra with its 800 Gb/s RAM. Max only goes up to 400 Gb/s.

ls612 on Feb 23, 2024 [–]

Yeah but the ultra only goes in desktop platforms which may be limiting to some.

int_19h on Feb 23, 2024 | [–]

But that's no different from mid-to-high-end GPUs, which is what the original ask was about.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact