Run large language models locally
One-command local serving of open models with an OpenAI-compatible API: private, free inference on your own hardware.
The one-liner for local LLMs: 'ollama run llama3' downloads and serves models with a OpenAI-compatible API. The tool that made local inference a normal dev workflow
Who it's for
Developers who want to run open LLMs locally with a single command and a simple API.
Official links
Keep exploring
Concepts in the glossary
3 in catalog
Ollama runs on
2 in catalog