Ollama simplifies downloading and running open large language models locally on macOS, Windows, or Linux without requiring paid services. Users can interact with models via a CLI, a REST API, or client libraries.
Project overview
Ollama simplifies downloading and running open large language models locally on macOS, Windows, or Linux without requiring paid services. Users can interact with models via a CLI, a REST API, or client libraries.
Project type
AI Agent · Model Runtime
Use cases
Chat Assistants · Coding & Development
Deployment
Binary / CLI
License
MIT
Best for
Developers, general users, or researchers on macOS, Windows, or Linux who want to run open models locally via CLI, API, or libraries.
Users who require a local_only data boundary and have no dependency on paid external services.
Key capabilities
Run and chat with large language models locally via CLI or REST API.
Provides a REST API for running and managing models.
Launch specific integrations for coding assistants like Claude Code, Codex, and Copilot CLI.
Limitations and risks
GPU acceleration support and minimum hardware requirements are not documented.
Telemetry collection practices and opt-out controls are not documented.
Getting started
Install the application using a one-line script for macOS, Windows, and Linux, or use the official Docker image.
After installation, run your first model using the CLI command `ollama run gemma4`.
Evidence and sources
GitHub project description: Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
README: Start building with open models.
README: curl -fsSL https://ollama.com/install.sh | sh
README: irm https://ollama.com/install.ps1 | iex
README: curl -fsSL https://ollama.com/install.sh | sh