Hacker News Reader

Comment by zymhan | Hacker News Reader

It drove me to setup Qwen 3.8 this weekend. I couldn't see the value in just giving them money for a higher tier plan instead.

I've never run a local LLM model before. Certainly won't take as long to iterate on this.

View on HN

Qwen 3.8 is excellent. With the right harness, it does about 95% of what Opus can do, in my case automation software development. Since 3.8 came out, I have significantly revised my expectations for a local model. Give it another year or two, and we'll be running fast and free local models for nearly everything that matters, and these costly subscriptions will be a thing of the past. I've always believed that AI should be free for everybody, like TV and radio. We're almost there.

What harness would you recommend? I’ve tried Pi but the model struggled to stay on track after the compaction.

I have only 48gb of ram, so can fit only 80k context max, so good compaction is must.

I am running it on 32GB and I did not saw model loosing it context even after 4-5 compactions in pi. I am running sessions for few days sometimes. I think it looped once, but loop police extension stopped it. The only problem I have know is how pi compaction works, which is forcing full prefill which takes time and it is erroring a lot. I wrote my own compaction that should remove full prefil but it does not work. But this is the only problem with this setup and it is more problem with pi then the model. I much more prefer it to use Qwen then paid models: Claude forces me to do reauth every other day and codex models either are too costly or not capable enough.

Free tv and radio? Where do you live? Where I live you either pay taxes for it, alternatively, it is so ad infested that it is not possible to watch it.

I suspect the same will/is happening with AI. Either you will pay for it, or it will be so ad infested that it will become useless.

Reply on news.ycombinator.com