Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Seems a bit like GNUS [0].
---
[0]: https://www.gnus.ai/
by wsc981 - OP this project has been abandoned for years, you didn't even check the last commit date?by viking_fullz
- The reason i want to run models at home is to be able to experiment on them, change things, see how they get better or worse.by novia
- Any updates here to make this work on more modern llms?by htrp
- I did a triple take. Many years old but an early ground breaking project. Has some exploratoy ideas a year or two ago last I looked. Crazy to see Petals at 16 frontage (at time of writing)by ProofHouse
- This is awesome. Now we also need distributed training of models!
- Distributed training is much harder than distributed inference but not impossible. See the recent development of DiLoCo at Nous Research and Prime Intellect.by woctordho
- Related. Others?
Run LLMs at home, BitTorrent‑style - https://news.ycombinator.com/item?id=37546810 - Sept 2023 (125 comments)
by dang - I have been thinking of something on these lines but with much smaller models. The entire model has to fit on a single computer. Host owner would choose the model they prefer, perhaps because they already use it. Then it is more about utilizing the GPU for LLM requests.
Peer to peer, consumers get to route their request to a host with compatible model. Consumers have to also contribute GPU but it does not have to be equal - I have not thought through the fairness part. Perhaps initially it starts with "create your friends group and have access to all the host nodes".
by brainless - Can't wait to run a Sybil farm of subsidized proxy nodes and log all the juicy prompts.by inigyou
- Hm, looks like this is an old project (2022) associated with HuggingFace (https://huggingface.co/bigscience).
Doesn't look like it's very active nowadays: https://github.com/bigscience-workshop/petals
Article with more details: https://techcrunch.com/2022/12/20/petals-is-creating-a-free-...
> [...] volunteers can donate their hardware power to tackle a portion of a text-generating workload and team up others to complete larger tasks, similar to Folding@home and other distributed compute setups.
by wxw - Maybe it's time to refresh this idea then. There's a clear demand for running LLMs at home, but the good ones are too big, and you're not using it most of the time. Sharing with others sounds like a perfect solution to me.by mcv
- That explains the very old models mentioned on the page. There are models you can run locally on anything that would be more useful than llama 2 70B. e.g. the new Prism Bonsai 27B ternary model is 6GB, runs on any modern Mac, any PC with a gaming GPU bigger than 8GB (12GB or 16GB would be better), and probably runs on CPU faster than this runs any of those models. Gemma 4 E2B or E4B or 12B in the QAT quantization are fantastic for their size, and run on a lot of stuff. Models at every level have gotten a lot better since 2022.by SwellJoe
- The recently discussed https://meshllm.cloud/ is the one I've been playing with but don't have the hardware to try with a model split between nodes, which apparently is supported and just not part of the public demo.by maccam912
- Can't even scroll the website on mobile, too much going onby atum47
- It's an interesting concept but the timing is probably too early. If more people had reliable low latency gigabit or ideally 10gbit throughput, then it might start to approach feasibility. There's other blockers too, but that springs to mind immediately.
It's cool to imagine a planet wide neural network interconnected with fiber - the nervous system of a planetary intelligence. But perhaps mushrooms do that already (Alpha Centauri ever relevant).
by N_Lens - A planetwide hallucination – sounds awful.by qmmmur
- What? LLMs are perhaps the least bandwidth-constrained thing you can do over the network.
If you run a local model at a good pace, you're emitting tokens at, what, 60 tokens/sec? That's, very roughly, 300 bytes/sec. You can get that speed with dialup from the 80's! And when it takes a half second just to ingest the input tokens (to get to the part where you start generating the reply), you're not gonna care about even a crazy 250ms latency.
Unless you think that the model should be downloaded on-the-fly in response to a user request, there's zero reason for an LLM to need any sort of fast connection.
by fwip - Too early? the project has been going for years now...by behnamoh
- Too early too in that later (hopefully) each node can serve a full model so it is then a simpler share tit for tat of complete models.by hahahaa
- Not a neural network though ;) https://biologyinsights.com/do-fungi-have-a-nervous-system-t...by c7b
- Relevant: Why Switzerland has 25 Gbit internet and America doesn't https://news.ycombinator.com/item?id=47652400by woctordho
- Petals is from 2022. Nowadays intelligence of smaller models, quantization techs, and optimizations to run models faster on consumer GPUs have improved a lot.
For distributed inference of smaller LLMs and diffusion models that fits in one consumer GPU rather than splits on multiple machines, there are already pretty good solutions such as AI Horde (formerly Stable Horde) [0]. Notably, it's the default provider that powers SillyTavern. It also has an interesting economy model of kudos.
by woctordho - > For distributed inference of smaller LLMs and diffusion models that fits in one consumer GPU rather than splits on multiple machines
But isn't what everyone want almost the complete opposite of this? For smaller LLMs you can already run them with consumer hardware, sometimes consumer hardware 2x, but it's the rest of the stuff where distributed inference could actually "democratize" access, as almost no one has 500GB VRAM available at home, or whatever the latest SOTA local models take nowadays.