Ollama

What It Does

Command-line tool for running LLMs locally. Pull models like Llama, Mistral, or Gemma with a single command and run them entirely on your hardware.

Available On

• Terminal / CLI - Mac, Windows, Linux
• Local API - OpenAI-compatible REST API
• Integrations - Used by Cursor, Aider, Open WebUI, and dozens of other tools

Key Features

• One-command setup - ollama pull llama3 and you're running
• Model library - Hundreds of models available to pull
• OpenAI-compatible API - Works as a drop-in local backend
• Modelfile - Customize models with system prompts and parameters
• Lightweight - Minimal overhead, runs as a background service
• GPU support - Metal (Mac), CUDA (Nvidia), ROCm (AMD)