Qwen was doing something like this with their coder models. But alas, they seem not to be releasing those anymore. Last one was Qwen3-coder-next.

▲

yousif_123123 5 hours ago | parent | next [-]

Its crazy that OpenAI and Anthropic themselves aren't doing that. No attempts at reducing inference cost for code as far as I know from them.

▲

andai 4 hours ago | parent | next [-]

OpenAI do have codex models, which are half the price. I haven't used them enough to comment on the quality though.

I remember them saying a few years ago that, they didn't think it was worth specializing models for code, because their general purpose models kept beating them. I guess they changed their mind? Since they did start making codex models again.

	▲	arcanemachiner 4 hours ago \| parent [-]
		They also stopped making them again.

▲

andriy_koval 3 hours ago | parent | prev [-]

My speculation is that frontier models are MoE, and they just have some number of experts for coding.

▲

gsibble 5 hours ago | parent | prev [-]

I use this model. It's pretty good but not Opus 4.8 or Fable levels obviously. I'm really hoping we get more models like it (and better) soon. I run it locally and it's great that way.

	▲	UncleOxidant 5 hours ago \| parent [-]
		Qwen3-coder-next is very usable. But I don't think it's as good as Qwen3.6-27B (though it does run faster on my hardware). It would be great if we could get a Qwen3.7-coder, but I'm not going to hold my breath.