Ollama

How do you run a language model locally with Ollama?

1. Install Ollama on your machine
2. Use the CLI to pull a model by name, such as 'ollama pull llama2'
3. Run the model using the CLI or access it through the REST API

What language models does Ollama support?

Ollama supports Llama, Mistral, Gemma, and dozens of other open-weight models. New models are added out of the box without manual configuration.

What interfaces does Ollama provide?

Ollama provides a command-line interface (CLI) and a REST API for running and interacting with language models locally.

Does Ollama cost anything?

Ollama is free to use and download.