Self-host Ollama + Open WebUI with Docker
A local LLM runtime paired with a ChatGPT-style web interface, for running open models on your own hardware.
This page describes the Levelrail template for Ollama + Open WebUI (AI). It deploys the services below as one Docker Compose app on your own server.
Project site: https://docs.openwebui.com/.Recommended memory: about 2048 MiB.
Services, ports and volumes
| Service | Image | Container ports | Volumes |
|---|---|---|---|
ollama-api | ollama/ollama:latest | none | ollama_data -> /root/.ollama |
open-webui | ghcr.io/open-webui/open-webui:main | 8080 | open_webui_data -> /app/backend/data |
Environment variables
| Service | Variable | Value |
|---|---|---|
open-webui | OLLAMA_BASE_URL | Preset in the template |
Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.
Deploy Ollama + Open WebUI with Levelrail
In the dashboard, open Apps, choose New app, then Browse templates, and select Ollama + Open WebUI. Review the Compose body and deploy.
With the CLI:
levelrail-cli templates deploy ollama-open-webui --name my-ollama-open-webuiSee Service template catalog for how templates work, and Getting started if you have not installed Levelrail yet.
More AI templates
All templates are listed in the self-host gallery.