News for hackers. Stuff that matters.
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by twotwotwo on Thursday November 06, 2025 @04:14PM (#45840512)
I think there is a lot of progress on efficient useful models recently.

I've seen GLM-4.6 getting attention for good results from a model smaller than Kimi (~350b) and seen it speculated that Windsurf based their new model on it.

This Kimi release is natively INT4, which should lower the cost of inference.

DeepSeek's v3.2-Exp uses their sparse attention technique to make longer-context training and inference more efficient. Its output's being priced at 60% less than v3.1, for what that's worth. They've also quietly made 'thinking' mode need fewer tokens since R1.

And though it's on the proprietary side, Haiku 4.5 approaching Sonnet 4 coding capability (at least on benches Anthropic released) also suggests legitimately useful models can be much smaller than the big ones.

There's not yet a really great model you can run locally, though I think "efficient to run + open so competing inference providers can run it" is real progress. And more important it seems like the trendline is in the right direction and pieces are being researched that, when used together, could make for really efficient useful models.

There are no comments on this comment yet.