News for hackers. Stuff that matters.

A comment on Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5. Parent comment

Re:Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5 by Aurornis on Saturday September 06, 2025 @04:51PM (#45152733)
M1 Max with 64GB has 400GB/s memory bandwidth.

You have to get into the highest 16-core M4 Max configurations to begin pulling away from that number.

[ Parent | on HN ]
Re:Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5 by wkat4242 on Saturday September 06, 2025 @11:57PM (#45155267)
Oh sorry I thought it was only about 100. I'd read that before but I must have remembered incorrectly. 400 is indeed very serviceable.
[ Parent | on HN ]