Ollama
Run LLMs locally with one command: `ollama run llama3`. Mac/Win/Linux supported.
The de-facto standard for running large models locally. Pull up a model with a single command `ollama run llama3`; supports Mac, Windows, and Linux.
Run open LLMs on your own machine — no API bills, no data leaving your device.
Key features
- Runs open models locally on macOS, Windows, Linux, and Docker
- Chat with models via CLI: ollama run plus a model library
- REST API and official Python and JavaScript client libraries
- One-command integrations with Claude Code, Codex, Copilot, and OpenClaw
- Customizable via Modelfiles for model behavior and prompts
Good for
- Developers building apps on local open models
- Running an AI assistant without sending data to the cloud
Stack & tags
PythonJavaScriptllmlocal-inferenceopen-modelsrest-apidockercli
Quick start
curl -fsSL https://ollama.com/install.sh | shFrom the project README on GitHub.
Screenshots
Screenshots from the project’s GitHub README.
Our in-depth review
We covered Ollama in detail: Ollama Review 2026: The Honest Verdict on Running LLMs Locally