Local AI Local AI Foundations

Install Ollama

Get Ollama running on macOS, Linux, or Windows

55 of 66

What is Ollama?

Ollama is a command-line tool for running local LLMs. It handles downloads, model files, and an OpenAI-compatible API in one package. It is the best choice for terminal-first workflows and automation.

Official site: ollama.com

Install

macOS and Linux

curl -fsSL https://ollama.com/install.sh | sh

Windows

Download the installer from the official site: ollama.com.

Verify

ollama --version

You should see a version number.

Start the service

On macOS and Windows, Ollama starts automatically. On Linux:

ollama serve

Pull a starter model

ollama pull llama3.2

This downloads the model weights. They are stored in:

~/.ollama/models/

Run your first prompt

ollama run llama3.2 "Write a bash script that backs up a directory"

Ollama prints the response directly in your terminal.

Working out which model to run this on? See The Codex. Packaging it as a reusable skill? See The Armory.