Want Your AI to Stay Private? Run a Fully Local LLM with Open WebUI + Ollama

The article shows how to run a fully local LLM using Open WebUI and Ollama to keep data on your machine.

Ollama provides a local API on port 11434 and models can be pulled with ollama pull and listed with ollama list.

Open WebUI runs in Docker and should use --network=host so the container can access the local Ollama API.

After starting the container, the chat interface is available at http://localhost:8080 for private, offline use.