News for hackers. Stuff that matters.
Re:A guide to open-source LLM inference and performance by varunshenoy on Monday November 20, 2023 @06:54PM (#38356755)
Absolutely. Looks like the M1 Ultra has 800GB/s of memory bandwidth and ~20 TFLOPS of compute.

The same calculations from the post should hold, except with these new values.

There are no comments on this comment yet.