Ollama

Ollama lets people run open models locally with zero data retention, or use cloud model access for building with open models. It supports macOS, Windows, and Linux, and is used for both day-to-day use and app development.

The service includes local model runs, cloud usage with pay-as-you-go pricing, and team and enterprise plans for shared billing, administration, access controls, and usage budgets. It also tracks model downloads and tokens served, and offers access to a range of named open models through its cloud pricing.

The tool includes docs for developers. Prompts are never stored or trained on when using the local experience.