Selfhosted

48311 readers

1144 users here now

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:

selfh.st Newsletter and index of selfhosted software and apps
awesome-selfhosted software
awesome-sysadmin resources
Self-Hosted Podcast from Jupiter Broadcasting

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 2 years ago

MODERATORS

HybridSarcasm@lemmy.world

HybridSarcasm@lemmy.hybridsarcasm.xyz

105

What is a self-hosted small LLM actually good for (<= 3B) (lemmy.world)

submitted 1 day ago* (last edited 1 day ago) by catty@lemmy.world to c/selfhosted@lemmy.world

56 comments fedilink hide all child comments

I've tried coding and every one I've tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I've tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can't really handle anything above 4B in a timely manner. 8B is about 1 t/s!

you are viewing a single comment's thread
view the rest of the comments

[–] CrayonDevourer@lemmy.world -1 points 7 hours ago* (last edited 7 hours ago) (2 children)

I'm not storing their data. I'm feeding it to an LLM which infers things and storing that data.

[–] catty@lemmy.world 2 points 2 hours ago (1 children)

Was this system vibe coded? I get the feeling it was...

[–] CrayonDevourer@lemmy.world 0 points 1 hour ago* (last edited 1 hour ago) (1 children)

There's not actually that much code. It's like 8 lines for an AI 'agent', and maybe another 16 lines for 'tools', and I'm using Streamlink for grabbing the audio stream, and pulseaudio has a 'monitor' device you can use to listen to what's playing on the speakers. Throw it on a very minimal linux distro on a VM, and that's it.

I don't do 'vibe coding', but that IS where I got the idea from. People who are doing 'vibe coding' nowadays aren't just plugging things into a generic AI, they're spinning up 'agents' and making tools via MCP and then those agents are tasked with specific things, and use the tools to directly write to files, search the internet, read documents, etc

[–] tfm@europe.pub 1 points 46 minutes ago

I'd also consider writing a script with AI, which you don't understand, as vibe coding. Basically if you wouldn't be able to do it on your own it's vibe coding.

[–] catty@lemmy.world 1 points 2 hours ago

lol. Way to contradict yourself.