Guide
How to Use Fetch with Ollama
Run AI entirely on your Mac — no API key, no cloud, no cost. Everything stays on your device.
Install Ollama and download a model
Go to ollama.com/download and install Ollama for macOS. Once installed, open Terminal and run a model — we recommend ollama run qwen2.5 or ollama run llama3.1. The first run will download the model automatically. Ollama runs silently in the background after that.
Connect Ollama in Fetch Settings
Open Fetch Settings and go to AI Configuration. Set the AI Provider to Ollama — Fetch will automatically detect whether Ollama is running on your machine. Once connected, select your downloaded model from the dropdown and start using AI instantly with no API key required.
You're all set!
Press Option + Space to open Fetch and start using your local AI model. Try t hello world to translate text, or just type any question — all processed locally on your Mac.
Good to know
Completely free
Ollama is open source and free forever. No subscription, no usage limits, no API costs.
100% private
Your prompts and responses never leave your Mac. No data is sent to any server.
Switch models anytime
Pull as many models as you like with ollama pull. Switch between them in Fetch Settings instantly.
Works offline
Once a model is downloaded, Fetch works with Ollama even without an internet connection.