Ollama

Package

Run open models on your own machine behind a local REST API

Price: Free, open source; cloud plans paid
Access: None locally; API key for cloud

About

Open-source runtime that downloads and runs open-weight models on macOS, Windows and Linux, with an optional paid cloud for larger models. Suits local development and private data. Speed depends on your GPU or unified memory.

What you can do with it

Download and chat with open models like Gemma and Qwen offline
Serve a local OpenAI- and Anthropic-compatible API for apps and coding agents
Generate embeddings locally for RAG without sending data to a cloud

Get started

Download Ollama for macOS, Windows or Linux
Pull a model with ollama pull

Example

ollama pull gemma4:e2b
curl http://localhost:11434/api/chat \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma4:e2b",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "stream": false
  }'

Details

Hosting: Hosted service, Self-hosted, Runs locally
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript
MCP server: None