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.

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.

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.

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

1. privacy obviously. I know you dismissed it but that’s really the biggest reason anyone will have.

2. 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.

3. 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.

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.

You can control the electricity source (renewable) at home and cool your system without wasting drinking water.

Because they want to. You can get your proofs yourself.

Probably best asking this in https://discuss.online/c/[email protected]

@[email protected] 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.

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.

What you ask for is impossible to prove, let alone test, without a rigorous definition of “insightful” or “accurate”.

“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!?”

Afaik most people who seriously want to have a local LLM start of off a pre-trained one from the internet…?

Take it to https://lemmy.world/c/fuck_ai we don’t care about this kind of rhetoric here