China's domestically developed open-source large language models have recorded more than 10 billion cumulative downloads worldwide, and the country now holds
I’ve stopped bothering using an editor with LLMs. I just get the model to make a phased plan, write using TDD, and tell it to do staged commits for each feature. Then I just review the diffs after.
I’ve stopped bothering using an editor with LLMs. I just get the model to make a phased plan, write using TDD, and tell it to do staged commits for each feature. Then I just review the diffs after.
Interesting. And for web search u use the built-in or hook it up to SearXNG?
I’ve just been using the builtin, but searxng might be better. Seems like a lot of people prefer it.
Thanks. The built-in uses Brave I think.
I think so yeah, searxng is definitely the most privacy focused option.
What model do you use and on what hw? I recently got a R9700 to experiment with the various Qwen 3.5/3.6 models.
I’m using 3.6 at 27bln and q8 on a M1 with 64gb.
What tps do you get on that?
Roghlt 10 to 13 tps give or take.