asenna

I don't think that's the right read. Deepseek Flash 4.1 1017 did not get affected much.

I think what's happening is Chines models genuinely try to benchmax on it and hence they suffer when a new version comes out.

You should be able to do some local LLM models on the M2 Max 64gb (Qwen 3.8 27b would be a strong model). I might go for that one.

Yep. I reviewed everything multiple times. And forgot to make the repo public :/

Have made it public now

With that kind of pricing, I don't think they're competing with GLM with this new launch.