Building a Home AI Server for Local LLMs (Ollama Setup)

Ever wanted to run powerful Large Language Models (LLMs) like Llama 3 or Qwen 3 right from your own home? This video is the start of that journey. I'm turning a pile of PC parts into a capable home AI server, and I'm taking you along for the entire process.

This is Part 1 of my new series on building a local AI agent. In this episode, we lay the foundation. I'll cover:
The hardware I chose for this budget-friendly AI rig.
Installing a lightweight, Arch-based Linux operating system (Omarchy).
Setting up the essential software, including Ollama to run the models and Gemini CLI for development.

If you're curious about self-hosting AI and want a realistic guide to building a PC for local LLMs, this is the perfect place to start.

In Part 2, we'll see if this build can handle more powerful models, and look at how to unlock its full potential.

*Subscribe to CoreWorx Lab for Part 2 and more AI and smart home projects!*

00:00 Intro
00:54 Build
02:41 Omarchy Install
03:24 1st Boot and Update
06:11 Install Ollama
11:38 Connect Open WebUI
14:25 Install Gemini-CLI
17:12 Outro

#localai #llm #ai #aidevelopment #ollama #custompc #diy #omarchy #gemini #geminicli