Local AI Model Server
170.0k 2026-04-26
ollama/ollama
Run open-source large language models locally on your machine with a simple CLI, REST API, and client libraries.
Core Features
Easy local deployment of LLMs (macOS, Windows, Linux, Docker)
CLI for managing and interacting with models
REST API for programmatic access and integration
Python and JavaScript client libraries
Support for a wide range of open models (Gemma, Qwen, etc.)
Quick Start
curl -fsSL https://ollama.com/install.sh | shDetailed Introduction
Ollama is an open-source platform designed to simplify the process of running large language models (LLMs) locally on various operating systems. It provides a user-friendly command-line interface, a robust REST API, and client libraries for Python and JavaScript, enabling developers to easily download, manage, and interact with a diverse range of open models. By bringing LLM inference to local machines, Ollama empowers users to build AI-powered applications, coding assistants, and personal AI tools with enhanced privacy and reduced reliance on cloud services.