Ollama

How to run LLMs locally with Ollama

Installation

brew install ollama

Uninstallation

Uninstalling ollama does not remove downloaded models!

brew uninstall ollama

rm -rf ~/.ollama

---

Running Ollama Server

• Once up and running, we can download and run models.

ollama serve

• Stop the server by hitting CTRL + C or by closing the Terminal session

---

Discovering and Downloading Models

• Models are viewable here

• Models are downloaded here ~/.ollama/models/manifests/registry.ollama.ai/library/

---

Command Cheat Sheet

List downloaded models

ollama list

View running models

ollama ps 

Running models

If the model isn't installed already, it will be downloaded

ollama run gemma3:27b

---

Integrating with VS Code

Ollama must be running for this to work — ollama serve