LinkedInGitHubYouTube

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

View running models

Running models

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

Integrating with VS Code

Ollama must be running for this to work — ollama serve

PreviousLM StudioNextAWS

Last updated

Was this helpful?