Ollama makes running large language models locally a one-line affair: pull a model like Llama, Qwen or Mistral and chat with it entirely offline. It exposes a local API that dozens of apps build on, and it's free and open source.
No reviews yet — be the first.
Ollama was added to the directory on Jul 7, 2026 and this page was last updated Jul 7, 2026. Spotted something wrong or missing? Contribute to this page.