Why host Open WebUI on a VPS rather than locally?
Local hosting works for testing, but it has real limits in production: it consumes machine resources, offers no remote access, and provides no high availability. A VPS solves these problems: it runs 24/7, is accessible from any device, and gives you full control.
What you get with a dedicated VPS for Open WebUI
- Access from any browser, anywhere in the world
- Data hosted on your own infrastructure — no leaks to third parties
- Share the interface with your team without complex configuration
- The ability to connect multiple models (Ollama, OpenAI API, Anthropic…)
- Dedicated resources: no slowdowns shared with other users
Prerequisites
Open WebUI requires Docker to run. Ollama (if you want to run an LLM locally on the server) is RAM-hungry. Plan for at least 4 GB of RAM for a 7B model, and 8 GB for a 13B model. If you only use external APIs (OpenAI, Anthropic), 2 GB of RAM is enough for the interface.
Deployment in 5 steps
Prepare your VPS
Order a Cloud VPS with Ubuntu 22.04 LTS. Update the system: apt update && apt upgrade -y. Enable the UFW firewall and allow the SSH (22), HTTP (80), and HTTPS (443) ports.
Install Docker
Install Docker Engine from the official Docker repository. Add your user to the docker group to avoid repeated sudo commands. Verify the installation: docker run hello-world.
Start Open WebUI
Pull the official Docker image and launch the container, exposing port 3000. Mount a volume to persist data across restarts. Open WebUI is accessible at http://votre-ip:3000.
Configure a reverse proxy (Nginx)
Install Nginx and set up a virtual host that proxies requests to port 3000. Use Certbot (Let's Encrypt) to obtain a free SSL certificate. Your interface will be accessible over HTTPS on your domain.
Connect your models
In the Open WebUI interface, configure your API connections: local Ollama, OpenAI, Anthropic, or any other compatible provider. Create user accounts as needed.
If you want to run an Ollama model directly on the same VPS, opt for a plan with at least 8 GB of RAM and NVMe SSDs to reduce model loading times.
