Model Backends

Overview

Margarita supports multiple model backends, allowing you to choose the one that best fits your needs. The available backends include:

Note: We're adding more backends all the time! If you have a specific model or provider you'd like to see supported, please let us know by creating an issue in our GitHub repository.

• Ollama: A local model backend that runs on your machine.
• GitHub Copilot: A cloud-based model backend that integrates with GitHub's

Switching Between Backends

Use the following command to switch between model backends:

margarita use <backend_name>

Ollama

Ollama is a local model backend that allows you to run language models on your machine.

margarita use ollama

GitHub Copilot

margarita use copilot