A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.
Rules:
Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.
No spam posting.
Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.
Don't duplicate the full text of your blog or github here. Just post the link for folks to click.
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
No trolling.
Resources:
Any issues on the community? Report it using the report flag.
Questions? DM the mods!
Heh, you shouldn’t be paying for LLMs. Gemini 2.5 Pro is free, and so are a bunch of great API models. ChatGPT kinda sucks these days (depending on the content).
I have technical reasons for running local models (instant cached responses, constrained grammar, logprob output, finetuning), and I can help you set that up if you want, but TBH I am not going into a long technical proof of why that’s advantageous unless you really want to try this all yourself.
100% you don't have to train a thing ollama uses open availability models. They many are decent, the best use a lot of ram/vram.
I want someone to prove his LLM can be as insightful and accurate as paid one.
Why would someone do that for you when they're happy using their local LLM?
"Why do people do X, when in my opinion if you disregard the two top reasons for doing X, it's pointless? Prove to me that it would be better!?"
Privacy would be the main concern. Every single one of your words, documents, pictures will probably end up in some large database over at OpenAI. I don't like that at all. And as a company for example, it might be against the law to share some information about clients with third parties.
Then you don't get any of the freedoms we got with Free Software. It's a service you rely on with very little opportunities to customize, or look inside and tinker. There is little control for the user whatsoever. Additionally we already had companies cease service. So it might become unavailable tomorrow, which is a bad thing if you're attached to it, invested or built things around it.
And since "the internet is for porn"... We also have a noteworthy community doing those kinds of things. And well... go ahead and ask the big services to generate a lewd story. Most of them even refuse to write a murder mystery story for me, instead they'll lecture me on how it is not ethical to murder someone. So that would be use-cases where local AI outperforms any of the market leaders.
Personally, I'm a bit opposed to the entire concept of letting other people's algorithms dictate my life. I don't want to rely on them. I also don't want them to pick the bias for my perspective on the world. The algorithms in social media are dwarfed by how dangerous it's gonna be once people rely on AI more and more. And it gets to choose which information to show and which to drop. What kind of bias to introduce in summaries etc. Teach people how to think. And I already don't like the way all big AI chatbots talk to me with a lot of emojis and in a "Explain like I'm 5 yo" way.
So to go back to the original question... I think the more "useful" AI is, the more reasons there are to retain some control yourself. What do you think?
Why do people host LLMs at home when processing the same amount of data from the internet to train their LLM will never be even a little bit as efficient as sending a paid prompt to some high quality official model?
inb4 privacy concerns or a proof of concept this is out of discussion, I want someone to prove his LLM can be as insightful and accurate as paid one. I don’t care about anything else than quality of generated answers
If you ask other people for their reasoning and opinions, it doesn't really make any sense to put something "out of the discussion", does it? :P
But no, if you have no qualms about sharing your innermost feelings, sexual preference or illegal plans with those that have an explicit desire to exploit that information then there is little reason to attempt something as complicated and wasteful as self-hosting your own LLMs.
want someone to prove his LLM can be as insightful and accurate as paid one.
The full DeepSeek model is available for download, and should generate about the same quality answers as the official one, with the bonus of less censorship. I pretty trivially got it to talk about the Tiananmen Square, and they can't even ban me for it.
That said, that's rarely the point. It's usually because you can, a cost saving measure, sometimes you plainly just don't need a good model, sometimes you want privacy, sometimes you need privacy at the cost of quality.
If your business is shoving customer reviews into a model, you really don't need the best model for it to tell you how angry the customer is.
Personally I just do it for fun and because I can. Sometimes you just do things for no other reason than because you can.
Poor internet connection/no internet at all, network latency too high for their needs, specific fine tuned LLM ?
Off course, main reason is privacy. My company host its own GPT4 chatbot, and forbid us to use public ones. But I suppose there are other legit use case to host its own LLM.
I want someone to prove his LLM can be as insightful and accurate as paid one.
I mean, you can train a model that's domain-specific that some commercial provider doesn't have a proprietary model to address. A model can only store so much information, and you can choose to weight that information towards training on what's important to you. Or providers may just not offer a model in the field that you want to deal with at all.
But I don't think that, for random individual user who just wants a general-purpose chatbot, he's likely going to get better performance out of something self-hosted. Probably it'll cost more for the hardware, since the local hardware isn't likely to be saturated and probably will not have shared costs, though you don't say that cost is something that you care about.
I think that the top reason for wanting to run an LLM model locally is the one you explicitly ruled out: privacy. You aren't leaking information to someone's computers.
Some other possible benefits of running locally:
Because you can guarantee access to the computational hardware. If my Internet connection goes down, neither does whatever I'm doing with the LLM.
Latency isn't a factor, either from the network or shared computational systems. Right now, I don't have anything that has much by way of real-time constraints, but I'm confident that applications will exist.
A cloud LLM provider can change the terms of their service. I mean, sure, in theory you could set up some kind of contract that locks in a service (though the VMWare customers dealing with Broadcom right now may not feel that that's the strongest of guarantees). But if I'm running something locally, I can keep it doing so as long as I want, and I know the costs. Lot of certainty there.
I don't have to worry about LLM behavior changing underfoot, either from the service provider fiddling with things or new regulations being passed.
Afaik most people who seriously want to have a local LLM start of off a pre-trained one from the internet..?
You can control the electricity source (renewable) at home and cool your system without wasting drinking water.
Because you don't train your self-hosted LLM.
As a result you only pay for the electricity of computing your tokens (your request), this can be especially reasonable if the same machine also does local game streaming and or transcoding, and thus already has the requirements to host a LLM.
If you don't have rather unreasonable means, your local LLM is just very much more limited in parameters (size), and will not be as good as other, much larger models.
Privacy, Ethics and personal interest usually are the largest drivers from what I can tell.
Because they want to. You can get your proofs yourself.
I want someone to prove his LLM can be as insightful and accurate as paid one.
Are you using LLMs as search engines?
Bold.
I use Gemma, LLama 3.2, and Deepseek to either fix formatting, summarize documentation to give me commands for Linux software, and write simple code structure for me to refine into working code.
Sure it takes longer to generate than a cloud compute would, but
privacy obviously. I know you dismissed it but that's really the biggest reason anyone will have.
this feels better environmentally. I actually don't know if that's true, but it objectively touches less computers for such simple tasks. It would be wasteful of infrastructure to do it over the web.
it's just cooler to have a conversation with my computer. I've learned a lot about how the whole process works and that's more valuable to me as a non dev than just getting the end results.
@Brylant@discuss.online if you are willing to dismiss all of the reasons someone would prefer self-hosting an LLM, then of course a paid one will fare better, you self-host LLMs for privacy, or to tweak things which you cant do with external services, plus, in some cases it can be cheaper if you dont need a giant model to do a few basic things.
What you ask for is impossible to prove, let alone test, without a rigorous definition of "insightful" or "accurate".