Hacker News new | ask | show | jobs
by brucethemoose2 926 days ago
2.65bpw, on a totally empty 3090 (and I mean totally empty).

I woukd say 34B is the performance sweetspot, yeah. There was a long period where allow we had in the 33B range was llamav1, but now we have Yi and Codellamav2 (among others).