Skip to main content

OS with Open WebUI app

You can install an OS with the pre-installed Open WebUI application on a dedicated server.

The OS image with Open WebUI is based on SelectOS — learn more about the OS in the SelectOS documentation. The parameters of available models (LLM, Large Language Model) depend on the hardware specifications of the dedicated server. The model will not run if its size exceeds the GPU VRAM size. Learn more about choosing a configuration for LLMs in the Machine learning models subsection of the Select components for a custom dedicated server instructions.

The OS image contains:

  • Open WebUI — a web UI that allows you to manage and interact with LLMs via Ollama;

  • Ollama — a platform for running LLMs locally on a server. It runs in the ollama Docker container, which does not have direct internet access and interacts only with the openweb-ui Docker container via the llm-net Docker network;

  • Docker — a containerization platform for developing and running containerized applications;

  • network component settings:

    • nginx — a web server and reverse proxy. Open WebUI does not support HTTPS directly. Nginx is used as a proxy server and provides access to Open WebUI over HTTPS; for this purpose, a self-signed TLS (SSL) certificate by IP address is generated in the system.
      For long-term work with the server, we recommend replacing the self-signed certificate with a trusted certificate for your domain and configuring nginx to work with it;

    • UFW (Uncomplicated Firewall) is a simplified command-line interface for managing the Netfilter firewall in Linux-based operating systems. UFW allows incoming connections only on ports 22, 80, and 443; all other traffic is blocked.

Before installing the OS with the application, review the software license agreements included in the image.

Install OS with Open WebUI

For Open WebUI to work, the dedicated server must be accessible from the internet.

You can install an OS with Open WebUI along with an LLM right away or install the required LLM after installing the OS.

  1. In the control panel, in the top menu, click Products and select Dedicated Servers.

  2. In the Servers section, open the server page → Operating system tab.

  3. Click Reinstall OS.

  4. Optional: for a secure connection to the server using the encrypted SSH protocol, select a previously uploaded and placed SSH key or add a new one. Learn more in the Create and upload an SSH key on a dedicated server instructions.

  5. Enter user data. You can use user data to automate server configuration. You can specify user data only for servers without hardware HBA and RAID controllers.

    To install an LLM, you need to insert a script into the user data field:

    #cloud-config
    runcmd:
      - ollama_pull hf.co/<llm_name>

    Specify <llm_name> — the creator and model name, for example, Qwen/Qwen3-30B-A3B-GGUF. Models in GGUF format are available for installation; learn more about available models on the Hugging Face website.

  6. In the Distribution field, select Open WebUI.

  7. Optional: partition disks. You can select the disk on which the root partition / will be created and the OS will be installed. If the server has four or more disks, you can combine them in pairs into different RAID levels, for example, RAID1 and RAID0.

    By default, the optimal RAID level is determined and only disks with partitions and disks in RAID are partitioned. If you leave the default partitioning, the OS will be installed on the first disk in accordance with the order of disk installation on the server — NVMe → SSD → HDD.

  8. Click Install. Installation may take from 7 to 60 minutes; its duration depends on server performance and the selected distribution. If more time has passed, create a ticket.

  9. After OS installation, a password to connect to the server will be generated. The password can be copied in the control panel: in the top menu, click Products → Dedicated Servers → server page → Operating system tab → in the Password field, click . The password is available for viewing for 24 hours from the start of OS installation or configuration change. If you forgot the server password, you can reset and restore it.

Connect to the Open WebUI panel

  1. Open the following page in your browser:

    https://<ip_address>

    Specify <ip_address> — the public IP address of the server. You can copy it in the control panel: in the top menu, click Products → Dedicated Servers → server page → Operating system tab → in the IP field, click .

  2. Click Get started.

  3. Create an administrator account:

    3.1. In the Name field, enter the administrator name, for example, Admin.

    3.2. In the Email field, enter an email address.

    3.3. In the Password field, enter the account password.

    3.4. Click Create Admin Account.

Install LLM

  1. Connect to the server via SSH or via the KVM console.

  2. Install the model:

ollama_pull hf.co/<llm_name>

Specify <llm_name> — the creator and model name, for example, Qwen/Qwen3-30B-A3B-GGUF. Models in GGUF format are available for installation; learn more about available models on the Hugging Face website.