Ollama

Run large language models locally with one command. A friendly CLI and API for Llama, Mistral, Qwen, Gemma and hundreds of open models on your own machine.

Ollama is a local LLM runner that makes open models as easy as a package manager. Pull a model, run it with ollama run, and talk to it through a built-in OpenAI-compatible API.

Key Features

One-command model install (ollama pull llama3.2).
Local, private inference — no data leaves your machine.
OpenAI-compatible API at localhost:11434.
Multimodal models for vision.
Model library with hundreds of curated tags.
CLI, desktop app and bindings for every language.

Pricing

Ollama is free and open source under the MIT license. Models carry their own licenses.

Getting Started

brew install ollama
ollama pull llama3.2
ollama run llama3.2

Query the API: curl http://localhost:11434/api/generate -d '{"model":"llama3.2","prompt":"Hello"}'

About

Pricing

Key Features

Pricing

Getting Started