Ollama
Download and run open LLMs locally behind a simple CLI and API
What it is
A runtime that downloads and runs open-weight models on your own machine and serves them over a local HTTP API. It has a CLI, a Docker image and Python and JavaScript client libraries, and can hand a local model to coding agents such as Claude Code or Codex. For anyone who wants local models without manual setup.
Good for
- Run an open model on a laptop
- Serve a local LLM API for other apps
- Point a coding agent at a local model
Install or run
curl -fsSL https://ollama.com/install.sh | shCommand as given in the project README. Read the repository before you run anything on your machine.
What you need
Enough RAM or VRAM for the chosen model
Sources
- https://github.com/ollama/ollama (project README, read 10 Nov 2026)
- https://api.github.com/repos/ollama/ollama (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.