logoalt Hacker News

disiplus • today at 7:44 PM • 1 reply • view on HN

this is properly bad as you can run glm on 6000pro, at (in my eyes) pretty good quant, and a q2 on a 5090. im suprised at how good 5.3 flash is at some parts. i still think ds4.1 flash is better but it is more demanding. i hope meta pushes something in a range of 300-400b with a 15-20b active parameters. i know its a crowded space. but it would be fast and probably mostly good enough.


Replies

Melatonic • today at 11:05 PM

Have you tried two 6000 Pro Blackwells with a model spread between both ?