looks like it's just qwen 3.6 coder.

its worse at code compared to qwen 3.6 coder.

	▲	stymaar an hour ago \| parent [-]
		How can it be worse than something that doesn't exist?

▲

SubiculumCode 3 hours ago | parent | prev [-]

Do you mean it's based on qwen 3.6 coder?

▲

daemonologist 3 hours ago | parent [-]

There is no "coder" version of Qwen 3.6; I think they just mean it's a coding-focused model of similar size and performance (to Qwen 3.6 35B-A3B).

Regular Qwen 3.6 benchmarks slightly better and has much wider software support though, so this is probably of interest only to organizations which disallow models trained in China.

▲

kadoban 3 hours ago | parent [-]

I mean, Qwen 3.6 kicks ass. I don't know who these people are, but if their first outing is "not quite as good as Qwen 3.6", that's not a bad start by any means.

30B vs 35B isn't nothing either.

If it ends up just being some tweaks to someone else's weights, then meh.

	▲	mtone 2 hours ago \| parent [-]
		It was trained from scratch by Cohere. They're the only Canadian AI lab - I'm glad they're releasing open weights and I wish them luck catching up!