Hacker News Reader

Comment by mft_ | Hacker News Reader

I’m frequently surprised how little I can find online about exactly this - different harnesses for local models and how to set them up. The documentation for opencode with local models is (IMO) pretty bad - and even Claude Opus (!) struggled to get it running. And so far I’ve not found a decent alternative to Claude Desktop.

(I’ve recently discovered that you can pipe local models into Claude’s Code and Desktop, so this is on my list to try).

View on HN

Qwen3.6 is brand new. But also, search engines are so plastered with AI slop that is written by tools and companies that have no interest in you using local models. Ollama makes it 1 command to run local small models, but with the newest ones there can be kinks to work out first.

/R/localllama is okay for some information but beyond that there is so much noise and very little signal. I think it's intentional.

Thanks. I’ve been experimenting with local models for over a year now, on and off, so this isn’t just limited to the latest Qwen. Anyway, I have no problem running them, but there’s a huge difference between running something via a chat interface and running it a la Claude Code so that it can interact with the local environment and create/edit files. This is the aspect that’s difficult, in my experience.

It’s all about tooling, if the ai can fetch data it can do something rad with it. Use something like an ai harness to have an mcp server and other tooling to improve the harness and the tools I made this for my own learning: GitHub.com/ralabarge/beigebox

Reply on news.ycombinator.com