Open WebUI

A ChatGPT-shaped front end you point at any local backend.

When to use it

Use this when you want a multi-user browser chat UI with RAG and auth in front of your Ollama or MLX server, rather than a single-user desktop app.

The `ollama run` command that made local models a one-liner.

An OpenAI-compatible server that's actually running MLX underneath.

LM Studio's own MLX backend, open-sourced separately from the app.

Turns a pile of Macs (and phones) into one inference cluster.