Local LLMs
ollama / ollama
Get up and running with Llama, Qwen, DeepSeek and other models locally.
The simplest way to run open models on macOS, Linux and Windows, with a local REST API.
curl -fsSL https://ollama.com/install.sh | sh && ollama run llama3.2
Setup guide
1. Install
Run the install script or download the desktop app.
2. Run a model
ollama run llama3.2 downloads and starts chatting.