Run AI Models Locally
Get hands-on with local AI — install Ollama, run models offline, and learn prompting techniques.
TUTOR WITH THEFOCUS.AI
Copy this prompt into Claude, ChatGPT, or any external AI assistant. It points the assistant to the course instructions and links it to your student profile to track your progress and customize observations.
You are not enrolled yet. Enroll to generate a Student ID to track lesson completions and store learning notes.
Run AI Locally
A weekend project for beginners who want to run AI on their own computer — no cloud, no subscription, no internet required.
What This Course Is
You’ve used ChatGPT. You’ve maybe used Claude. They’re amazing — but they run on someone else’s computer, cost money, and need the internet.
What if you could run an AI model on your own laptop, completely offline, for free?
That’s what this course is about. By the end, you’ll have:
- A local AI model running on your Mac
- A set of “spells” (prompting techniques) that make any AI model work better
- A fully automated pipeline that can generate code, run it, test it, and improve itself
- A chat application you built yourself
Who This Is For
This course is for beginners. If you can open a terminal and type a command, you’re ready. You don’t need to know Python, TypeScript, or any programming language. The AI will write the code for you.
If you’re an experienced developer, there’s still plenty here — the automation patterns, the prompt-engineering spells, and the iterative self-improvement loop are valuable at any level.
What You’ll Learn
| Section | Skills |
|---|---|
| 01 Getting Started | Install Ollama, choose a model, run your first prompt, turn off Wi-Fi and watch it still work |
| 02 Prompting | Three “spells” that dramatically improve AI output: clarifying questions, YAGNI, and one-shot prompts |
| 03 Automation | Build a prompt runner, create a self-improving feedback loop, extract and execute generated code |
| Projects | Five real projects the AI builds for you — a weather CLI, file combiner, data extractor, prompt runner, and chat REPL |
The Philosophy
This isn’t a typical tutorial where we explain abstract concepts and then have you fill in the blanks. Instead, we:
- Talk to the AI — you’ll have real conversations with Ollama, just like you do with ChatGPT
- Get our hands dirty — copy code, run it, watch it break, fix it
- Build real things — every exercise produces a working program you can actually use
- Learn through iteration — we don’t get it right the first time, and that’s the point
By the time you’re done, you’ll have a mental model for how to work with AI that applies whether you’re using a local model or a cloud API.
Ready?
Start with About → to get your prerequisites and setup sorted.