Hacker News Reader

Comment by varispeed | Hacker News Reader

> that local models are good enough for whatever they're peddling

they are not. Unless you are satisfied with plausible, but mostly garbage output.

They are actually quite a bit better than you might think. Qwen3.6 27B is pretty capable at coding.

For non-coding work, they are more than good enough. A lot of the ways my non-technical family members have interacted with AI would be perfectly served by using a local model.

After all, people were more than satisfied with the results from GPT 3. That has long since been surpassed by open weight models.

I'm sure there are things local models are good enough at in non-coding work, but for anything complex I do not find this to be the case.

I'd say local models are fairly capable of even somewhat complex coding execution. For complex non-coding work (research, in-depth analysis, assembly of complex info-dense documents) I'd rather do it by hand than switch from Opus 4.7 to anything I could even theoretically run locally.

I don't know what kind of coding, but for my case it's been useless. Not working code almost every time. It's much quicker to just write it by hand than use that model.

I've been experimenting with Qwen3 Coder Next and Copilot for a little Rust toy project and it's been trucking along. It does require a fair bit of hand-holding (or perhaps I just don't trust it to give it larger tasks), but it works alright.

Give 3.5 or 3.6 a shot. 3.5 has smaller models that you could leverage. If you can swing it, though, 3.6 27B is quite good.

I get results comparable to the saas. Maybe Anthropic sold you too much crack tokens.

I suspect that a lot of people are ignoring the shift to a model where you feed entire specifications to a group of models in differing configurations controlling different aspects of the development task. In that model it doesn't really matter how fast the tokens are generated, only that they are eventually generated and that the assembly is good enough. It's a specification compiler at that point.

Multi-agent bread and butter.

Honestly, that's the output I get from non-local models, anyway. If I'm going to get plausible nonsense either way, I may as well run it on my own hardware.

That's all LLMs can give you anyway.

isn't that literally all output an LLM generates?

Reply on news.ycombinator.com