Wrote up a Windows-specific Ollama setup guide — CLI reference, env vars, Open WebUI pairing
- 1 Followers
- 0 Following
- 0 Posts
Well I appreciate your guys’s input but honestly I wish I would have found something like this when I first started off trying to figure out how to get in a abliterated model running on my computer without paying sub fees it probably took me a week or so to sift through everything and find what would actually work, this guide is literally designed for a beginner in ai inclined walked through the whole process. It’s genuinely useful for a very beginner. Most the stuff out there I found I had to have a dictionary with me essentially to understand and that alone can be a deterrent for some people. This guy couldn’t be any more simple and straightforward, lowering the barrier to entry for non-techy users. Givin, there may not be very many of those here but you never know. This probably people out there that would be afraid to jump on a form like this and ask cuz they’d probably get treated like they were stupid, we’re jumped on or whatever… my guide eliminates that factor by being genuinely helpful and plain simple.
I made a step-by-step guide for running AI locally on Windows
Ollama + Open WebUI on Windows: a fully open-source local AI stack, no cloud, no account
Your Windows 11 PC can run AI completely offline — put together a setup guide if anyone's curious
Your Windows 11 PC can run AI completely offline — put together a setup guide if anyone's curious - Lemmy.World
I’ve had several people ask me how to set local AI up on a laptop or desktop computer so I decided to make a guide that cuts through a lot of beginner confusion. I run Windows, so I put wrote out the windows guide first, will do a writeup for Linux and Mac if I see any demand or requests. My guide Covers both LM Studio and Ollama, plus Open WebUI if someone wants a browser interface instead of working purely from a terminal. Goes through model picks by RAM (what’s actually usable at 8/16/32/64GB+), GPU offloading, and a troubleshooting section for the stuff that actually trips people up — port conflicts, CUDA OOM errors, Ollama not showing up in PATH, that kind of thing. It’s a paid guide, $10, https://indigonynja.gumroad.com/l/jqwisc [https://indigonynja.gumroad.com/l/jqwisc] Happy to answer questions in the comments tell me your RAM/GPU and I’ll line out what to run, *I’m not an expert and I’m sure there’s other people on here that another stuff a lot better than me but I’m happy to help and any support is greatly appreciated!
Wrote up a full guide for running AI locally on Windows (LM Studio + Ollama + Open WebUI)
