alt Hacker NewsHalfway thru the article it shows a comparison with several frontier-ish LLMs. But they're all from half a year ago. "Our new model is better than all these Chinese models from 3 generations ago" is pretty funny to me.
Replies
rtaylorgarlock • today at 2:17 AM
Agreed, though open weights + relatively small is still headline worthy. This thing really cooks.
It’s a 6bn model. Totally different class. I’m more excited about “frontier small language models” tbh.