Learn

Local AI on Linux

Run, tune, serve and secure AI models on your own Linux machine.

Six chapters and a final test on an 8 GB Linux lab machine with no GPU: what a model file holds, running models with Ollama, the settings that change answers, quantization, serving over an API, and securing models.

1 published lesson across 1 chapter, about 1 hour of work. Every lab runs on a real virtual machine in your browser, and checks your work on the machine itself.

Published chapters and lessons

What a model is

What a model file holds and how to check it: weights and parameters, tokens and the context window, training and running, open and closed weights, and licences. Download a model file, verify its SHA-256, read its GGUF metadata, count its parameters and tokenize a sentence.

• Chapter 1. What a model is - Chapter 1 lab: What a model is. Five objectives on a real Ubuntu 24.04 machine with no internet: download Qwen3 0.6B from the machine's mirror, check it with sh

Frequently asked questions

How many published lessons are in Local AI on Linux?

Local AI on Linux has 1 published lesson, roughly 1 hour of guided work, spread across 1 chapter.

Do I need my own server or hardware to do the Local AI on Linux labs?

No. Every lab boots a real virtual machine in your browser, with a real Linux shell. There is nothing to install, and nothing on your own machine to break.

What level is Local AI on Linux?

Labs in this track are rated beginner. The track starts from the beginning, so no prior experience is assumed.