Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on MiniMax M2.1.
Looks like this is 10 billion activated parameters / 230 billion in total.
So, this is biggest open model, which can be run on your own host / own hardware with somewhat decent speed.
And looking at the benchmark scores - it's not that far from SOTA.
There are no comments on this comment yet.
Looks like this is 10 billion activated parameters / 230 billion in total.
So, this is biggest open model, which can be run on your own host / own hardware with somewhat decent speed.
And looking at the benchmark scores - it's not that far from SOTA.