Ollama

by Ollama

The easiest way to download and run open models on your own computer.

182.8 k stars GitHub MIT Free when localLocalOpen sourceOpen weights

View on GitHub →

What it does

One command to run Gemma, Qwen, Llama, DeepSeek…
Local API on port 11434, supported by most tools
"ollama launch" plugs straight into Claude Code, Codex or opencode

Install it

Requirements: macOS, Windows or Linux; an NVIDIA, AMD or Apple Silicon GPU is a plus.

Install (macOS / Linux)

curl -fsSL https://ollama.com/install.sh | sh

Install (Windows PowerShell)

irm https://ollama.com/install.ps1 | iex

Run a model

ollama run gemma4

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install Ollama (https://ollama.com) on my machine.
1. Check the requirements: macOS, Windows or Linux; an NVIDIA, AMD or Apple Silicon GPU is a plus. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install (macOS / Linux): curl -fsSL https://ollama.com/install.sh | sh
- Install (Windows PowerShell): irm https://ollama.com/install.ps1 | iex
- Run a model: ollama run gemma4
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.