Skip to content
Deploy

GPU servers · Apps

GPU server apps: what you can run and how to install it

Updated

A RyzenRDP GPU server runs Ubuntu 24.04 LTS with NVIDIA CUDA and gives you root access over SSH. You install the AI software you want on it yourself. The most common choices are Ollama and vLLM for language models, Open WebUI for a chat interface, ComfyUI for image and video workflows, and PyTorch with JupyterLab for your own code. This page lists what each one does, the command that installs it, and the port it listens on.

  • Root access over SSH
  • Ubuntu 24.04 LTS with NVIDIA CUDA
  • Commands from each project's own documentation

There is no one-click installer, and you do not need one

We do not preinstall these apps or install them for you. Each one installs with a few commands, shown below, and installing it yourself means you choose the version and know exactly what runs on your server. Start every new server with nvidia-smi, which lists the GPUs and their memory.

AI apps for a GPU server

Seven tools cover most of what people run on a GPU server. Each row links to the project's own documentation, which is the source to follow when a command changes.

Common AI apps for a GPU server, what they do and where they listen
AppWhat it doesListens onDocumentation
OllamaDownloads and runs language models with one command; offers an OpenAI-compatible API127.0.0.1:11434Ollama on Linux
vLLMServing engine for language models that batches many requests and can split a model across GPUs; OpenAI-compatible APIlocalhost:8000vLLM quickstart
Open WebUIBrowser chat interface with user accounts, for Ollama or any OpenAI-compatible endpointPort 3000 with the documented Docker commandOpen WebUI quick start
ComfyUINode-based interface and API for image, video and audio generation workflows127.0.0.1:8188ComfyUI repository
TextGenInterface for running and chatting with local language models, formerly known as text-generation-webui127.0.0.1:7860TextGen repository
JupyterLabNotebooks in the browser for experiments, data work and training codelocalhost:8888JupyterLab installation
PyTorchThe deep learning framework most models and training scripts are written inNo port: a Python libraryPyTorch: start locally

Ollama

Ollama is the shortest path from a new server to a model that answers. Install it with the script from its documentation, then pull and run a model:

curl -fsSL https://ollama.com/install.sh | sh
ollama run MODEL_NAME

The installer sets Ollama up as a systemd service that listens on 127.0.0.1:11434. ollama ps shows whether a model is loaded on the GPU. To let another program on the same server use it, point that program at http://127.0.0.1:11434. The OLLAMA_HOST variable changes the bind address, but Ollama has no sign-in of its own, so do not expose it to the internet. More on LLM hosting.

vLLM

vLLM is a serving engine for an API that many users or an application call at once. Its quickstart installs it into a Python environment with uv and starts an OpenAI-compatible server:

uv venv --python 3.12 --seed
source .venv/bin/activate
uv pip install vllm --torch-backend=auto
vllm serve MODEL_ID --api-key YOUR_SECRET_KEY

The server starts on http://localhost:8000. --api-key makes it reject requests that do not carry your key, and --tensor-parallel-size set to the number of GPUs splits one model across them. See vLLM vs Ollama for when to choose which.

Open WebUI

Open WebUI gives a team a chat interface in the browser, with accounts and conversation history, in front of Ollama or any OpenAI-compatible endpoint. It runs as a Docker container; install Docker first, then use the command from the Open WebUI quick start:

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data -e WEBUI_SECRET_KEY=your-secret-key \
  --name open-webui --restart always ghcr.io/open-webui/open-webui:main

Replace your-secret-key with the output of openssl rand -hex 32. The interface is then on port 3000 of the server. The first account you create becomes the administrator, so create it before you let anyone else reach the port. A private AI server is usually this: a model runtime with Open WebUI in front.

ComfyUI, TextGen, JupyterLab and PyTorch

  • ComfyUI installs from its repository with git clone, a Python environment and python main.py. The ComfyUI server page has the full steps and the SSH tunnel to reach it.
  • TextGen (formerly text-generation-webui) is started with ./start_linux.sh from its repository, which sets up its own environment on the first run.
  • JupyterLab installs with pip install jupyterlab and starts with jupyter lab. It prints a link with an access token; open it through an SSH tunnel.
  • PyTorch installs with pip install torch inside a virtual environment. Confirm it sees the GPUs with python -c "import torch; print(torch.cuda.is_available(), torch.cuda.device_count())".

Reach a web interface safely

  1. Leave the app on localhost

    Most of these tools listen on 127.0.0.1 by default. That is the safe setting on a server with a public IP address: keep it.

  2. Use an SSH tunnel for yourself

    ssh -L 8188:127.0.0.1:8188 root@YOUR_SERVER_IP forwards a port to your own computer, where you open http://127.0.0.1:8188. Change the number to the app's port.

  3. Use a reverse proxy for a team

    To share an interface, put a web server such as Caddy or nginx in front of it with a domain name, TLS and sign-in, or connect the team through a VPN such as WireGuard.

  4. Close everything else

    Allow SSH and only the ports you actually publish in the server's firewall, for example with ufw.

Which app for which job

GPU server apps FAQ

Are AI apps preinstalled on a RyzenRDP GPU server?

No. The server runs Ubuntu 24.04 LTS with NVIDIA CUDA, with no AI apps installed. You install the apps you want over SSH; the commands for the common ones are on this page.

Is there a one-click installer for Ollama or ComfyUI?

No. Each app installs with a few commands from its own documentation. That takes minutes and leaves you in control of the version.

How do I check that the GPU works?

Run nvidia-smi after you sign in. It lists each GPU of the server with its memory and current use. Inside Python, torch.cuda.is_available() confirms that PyTorch sees the GPUs.

Can I use Docker on a GPU server?

Yes. You have root access, so you can install Docker and run containers. To give a container access to the GPUs, install the NVIDIA Container Toolkit and start the container with --gpus all.

Which app should I use to serve an LLM?

Ollama for the simplest setup and a few users, vLLM for an API under real load or a model split across several GPUs. Both offer an OpenAI-compatible API. See LLM hosting.

Can I run Windows apps on a GPU server?

No. GPU servers run Linux only. For a Windows desktop over Remote Desktop, see our Windows VPS plans, which have no GPU.

Run your AI stack on your own GPU server

1, 2, 4 or 8 NVIDIA RTX PRO 6000 Blackwell SE GPUs with 96 GB of VRAM each, in Frankfurt, Germany. From $1,951.09 a month.