logoalt Hacker News

UncleOxidantyesterday at 5:55 PM0 repliesview on HN

Something in the 60B to 80B range would still be approachable for most people running local models and also could give improved results over 31B.

Also, as I understand it the 26B is the MOE and the 31B is dense - why is the larger one dense and the smaller one MOE?