• Chat
  • Beginner

A home ChatGPT with Ollama + Open WebUI

Get a multi-user, model-switching chat assistant with a web UI running on your own machine in ten minutes — usable from any phone on your LAN.

A home ChatGPT with Ollama + Open WebUI
Models
qwen3, llama3.1, gemma3
Tools
Ollama, Open WebUI, Docker
VRAM / RAM
8GB+
Platforms
Mac, NVIDIA, CPU only
Original source
docs.openwebui.com

Sample entry showing the structure of a play page. Delete it and add your own.

Setup

  1. Install Ollama and pull a model:
ollama pull qwen3:8b
ollama run qwen3:8b "Introduce yourself in one sentence"
  1. Start Open WebUI with Docker:
docker run -d -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data \
  --name open-webui ghcr.io/open-webui/open-webui:main

Open http://localhost:3000. The first account you register becomes the admin.

Going further

  • Create accounts for family members and reach it on your LAN at http://<your-ip>:3000
  • Turn on Documents, upload PDFs and do simple knowledge-base Q&A
  • Load two models side by side and compare their answers to the same prompt