About
A private ChatGPT on your Raspberry Pi. Ollama runs the model, Open WebUI gives you the chat. Small models, no cloud, nothing leaves the device.
Notes
Self-hosted local LLM stack: Ollama (model runner) + Open WebUI (ChatGPT-style frontend). The agent pulls the model you select on first install and serves the WebUI on the bound domain.
On a Pi 5 with 8 GB RAM, 4B-parameter quantised models like qwen3:4b or llama3.2:3b produce a few tokens per second on CPU and are usable for personal tinkering. Anything larger will swap.
Ollama always exposes its OpenAI-compatible API on obacht-<instance>-ollama:11434/v1 inside the obacht-edge network, so other instances on the same device (n8n, custom apps) can consume it via a service_reference config field of interface openai_compatible.
Toggle expose_ollama to true if you also want to bind a separate domain to the raw Ollama API for use from outside the device — otherwise only the WebUI is publicly reachable.
Heavy: needs ~3 GB RAM idle, several GB of disk per model. The models volume is preserved across reinstalls.
Alternative to: ChatGPT
Facts
- Version
- 1.0.2
- Source
- Official
- Runtime
- Several containers
- Devices
- Pi · Linux
- Min. RAM
- 4 GB
- Project
- openwebui.com
Install
How to run Ollama + Open WebUI yourself
- 01
Connect a device
A Raspberry Pi, a Linux machine or a Mac that is on anyway.
- 02
Install it
One click in your Obacht account. Your device checks the signature before anything runs.
- 03
Open it from anywhere
It gets a web address under your-name.obacht.space, with HTTPS. Add your own domain if you have one.
Open-source contribution
Forwarded
A fixed amount per install goes to Open WebUI, forwarded via GitHub Sponsors.
Ollama in this bundle can't take money. The contribution goes in full to Open WebUI.
Run it on your own hardware.
Obacht is in a closed pilot phase. Put yourself on the list. We let people in a few at a time, so it can take a while.