LocalLLaMA
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
Thank you for your opinion & recommendations. Something I saw today related to "sub-agents" is in Kimi 2.6's model card it says
So maybe Kimi 2.6 is doing the "type of thing" I am looking for, but I don't have the means to run it practically. Maybe at 1 token per second which would be brutal.
I tried out Qwen 3.6 27B but not yet in an agentic setting, so I can't really judge yet. Maybe it's just me but the small model size seems limiting. I thought gpt-oss-120b was good.
I suspect you may need to create your own orchestration to achieve the effect you're after. As I said, I have some ideas...but it's an engineering proposal, not a drop in replacement.
I'm actually creating my own micro swarm (literally as I type this; waiting for Codex to finish running smoke tests); I have a feeling if you want "Claude at home", you're going to have to uplift something like Qwen 3.6 + swarm + harness.
I could pass the idea on to you and you could get Claude to chew through it and see what you two could jury rig?
Sure, if you have a micro swarm architecture laid out, I would love to hear what it is.
I don't think my micro swarm architecture applies to your use case (I'm doing some funky stuff with sentence transformers as classifiers; well...it's a bit more than that but still, not coding related work), but I do have an end-to-end scoped draft for the coder up-lift. I had the basic idea iterated via me-codex-claude-me-codex-claude back and forth. I'll DM it to you just now; feed it into whatever you use (Opus, Codex, GLM) and see if it suits your purposes, broadly. You'll likely need to refactor it slightly, as Python is my poison of choice, but the broad brush strokes should hold.
Do me a favour and let me know what the clankers say / if it suits your purposes. And if you decide to build it and become rich, give me a shout-out LOL