[AIT] Local LLM for Server Setup Guidance?
from Lumisal@lemmy.world to selfhosted@lemmy.world on 26 Jul 16:24
https://lemmy.world/post/49925060
from Lumisal@lemmy.world to selfhosted@lemmy.world on 26 Jul 16:24
https://lemmy.world/post/49925060
Looking for a recommendation on an LLM that can guide a user on how to manually set up a home server that runs Jellyfin, Arr Stack, etc. Have a couple of friends interested and I have some spare old NUCs I was going to give them, so I was going to download the software for them and then walk them through it.
But it’ll be difficult to align our schedules for the next month or so (school starting and different time zones) so then I thought maybe I could just run an LLM they could use on my main PC for when they have time.
Why not just use one of the existing services? Those cost extra money and none of us want to financially support those companies.
threaded - newest
Probably setup ollama with qwen and aider first. Then give it the docs for the things you want to set up.
I have the Alpaca Flatpak, can I set this up in that or is Ollama better? I’m running on Debian
Never used alpaca. So I can’t help there.
Please update your title with [AIT] as noted in the sidebar.
Someone started a stack named admirarr but it miss the configuration of many parts. If you find something keep us updated.
I’ll give a non-answer; if they dont spend the time setting it up themselves to understand it, they are kinda screwed.
There are TONS of videos out there, step-by-step guides, that should be enough honestly. I understand the appeal of LLM though to talk through stuff, but honestly, just give them a good guide. They can ask Googles AI if they need terms explained etc.
Just a different perspective.
Any step-by-step text guides you’d recommend? They’re not exactly tech beginners, but they’re also not quite knowledgeable yet. I guided them through Linux install but they use Bazzite and mostly stick to Bazaar on it for any programs they need.
Maybe a easier place to start is a beginner friendly system? Lots of people like running Unraid for example, and they have lots of apps that will make it easier to get into (ca.unraid.net), that might help ease them into it. Being thrown into a Linux terminal might feel daunting, but also a great way to learn.
I think many just need to get hooked on it, then they more naturally feel like they want to customize and try out stuff.
I dont have any guide recommendations, since its been a while since I started. You can probably do some searching on the stuff you want them to setup.
I asked mostly because I haven’t seen any guides like that. The long video guides are also usually outdated or a very specific method that’s more advanced (like bare metal setup or using ignition)
My plan was to lead them through something like what I use which is base Debian using Dockge and a reverse proxy (though I’m looking into KDE Plasma BigScreen). I think they might be able to figure it out with help and some general written instructions and the AI for further questions.
For the arr stack the best resource I know is wiki.servarr.com which I referenced for my setup in Kubernetes.
Most projects have pretty good documentation on how to setup their services, in many cases its just the Docker config afterall.
I’d give that a +1. Anytime you put a little sweat into something, it makes it a bit more valuable to you.
why would anybody think that setting up a local “LLM that can guide a user on how to manually set up a home server that runs Jellyfin” would be easier than setting up jellyfin itself?
🤔
just follow the instructions on jellyfin.org/docs/general/installation/linux/#deb…
And the Arr Stack, and KitchenOwl, and LibreCloset. They also want something for YouTube, but haven’t decided what they might like the most yet - was thinking of testing KDE’s new Plasma BigScreen and seeing how Waydroid does at running S-tube.
If that worked well enough, then I’d probably try setting them up with that
GPT4All can accommodate a plethora of models all the way until you run out of VRAM. LOL Maybe play around with some of them. Right now I’m experimenting with DeepSeek R1 Distill Qwen 14 B, and Qwen 2.5 Coder -32B Instruct GGUF. Pretty neat stuff.
Is GPT4all still up to date though? I see the last release was in 2024
Release v3.10.0 dropped on Feb 24, 2025, so yeah it does have a little age. I’m not sure how often they would need to update the front end, as it seems the models are the driving force.
Mature software doesn’t need hourly updates. All the shit that leverages the library repos in horribly unsafe ways - ohai npm - that stuff needs constant updates.
Easy setup would be to use koboldcpp + SillyTavern + Gemma 4 26B A4B GGUF of the largest quant your graphics card can fit together with your context.
Remember to setup SillyTavern to allow network connections and create a user and password, default installation is localhost only.
Set the temperature to 0.3 if using IQ3_M, higher quants allow higher temperature, and make sure all the formatting templates inside Advanced Formatting are set to Gemma 4.
Then use either Gemma 4 itself or the free google.com AI to create some “W++ Denze with Horizontal Lines summaries for Gemma 4” of the relevant documentation of the latest version of the home server apps your friends are gonna install.
You should ensure the resulting lorebook entries are no more than 1k tokens each to leave some context for your friends chats, add it to a character card in SillyTavern and set some keywords to allow them to load dynamically and not stay in context memory all the time.
Regarding the character card you can ask Gemma 4 to write that for you too, I find “Write a character card in W++ Denze with Horizontal Lines style for Gemma 4 with this name, personality, attitude and skillset” works well for that.
Then ask it to write a “First message prompt that starts with X, continues with Y and ends with Z for that character card” and you get a first draft to rewrite and paste into the “First Message” of the character card. The first message works as a template that Gemma 4 will imitate when you chat with it. Then simply try the chatbot out before letting others use it.
I find my own Gemma 4 26B A4B IQ3_M works well for practicing hiragana and katakana, discussing programming or troubleshoot existing code or writing a small function but it can’t be expected to write a correct DatabaseService.cs from scratch and stuff like that.
Oh and forget about finding good cards and lorebooks for SillyTavern use online, most users use it for NSFW Roleplaying chats. It is a very easy UI to use to create harnesses for your local LLM though.