Llamafile on a VPS: Portable LLM Inference in One File
A llamafile bundles an LLM's weights and the llama.cpp runtime into one executable. Learn how to run it on a VPS, expose an OpenAI-compatible API, secure port 8080,…
Tutorials
Deploying Text Generation WebUI on a GPU VPS
Deploy Text Generation WebUI on a Contabo GPU VPS: clone the repository, load a model, and reach the browser interface over an SSH tunnel. You can also enable…
Setting Up lldap for Centralized VPS Authentication
lldap gives self-hosters a lightweight LDAP server without the usual complexity — here's how to set it up on a VPS.
SGLang vs vLLM: Which Inference Engine Fits Your GPU VPS?
SGLang vs vLLM compared for self-hosted LLM inference — how they differ and which fits your workload on a GPU VPS.
Self-hosting Boop: a tiny notification inbox for developers
Boop is a self-hosted notification inbox that pushes events from your apps to your iPhone. This guide covers deploying it on a VPS with Docker, connecting Apple push…
Wan 2.2 Video Generation with ComfyUI: A GPU VPS Setup Guide
A step-by-step guide to running Wan 2.2 video generation in ComfyUI on a GPU VPS, from installing ComfyUI and downloading the model files to loading the native workflow…
Stop Paying for SaaS: A Self-Hosting Starter Roadmap
Start by auditing what you're actually paying for, then replace one tool at a time — not everything at once. The order that works: set up your server…
Running KoboldCpp for local LLM inference on a VPS
KoboldCpp turns a VPS into a private LLM server with a web interface and an API. This guide covers what the tool is used for, how to deploy…
Self-Hosting SGLang: Fast LLM Inference on a GPU VPS
Deploy SGLang for fast, self-hosted LLM inference on a GPU VPS — what it is, how it installs, and when it's the right choice.
GPU VPS Pricing: Is Contabo the Cheapest GPU Cloud in 2026?
What you need to know Contabo GPU VPS costs $1,199 a month for one NVIDIA RTX PRO 6000 Blackwell Server Edition, with 96 GB of video memory on…
What Is BentoPDF? A Privacy-First, Self-Hosted PDF Toolkit
BentoPDF lets you run a private, self-hosted PDF toolkit on your own Contabo VPS. See how the client-side architecture works, how to deploy it with Docker, and which…
Self-Hosting Supabase on a VPS: What You Need to Know
Self-hosted Supabase gives you a full Postgres-backed backend on your own server. This guide covers the 11-container Docker stack, minimum VPS requirements, deployment steps, and how Contabo fits…
Setting Up a CS2 Dedicated Server: A VPS Hosting Guide
Host your own CS2 dedicated server on a Contabo VPS — requirements, SteamCMD setup, and port configuration + Self-hosted vs. Managed!
How to Host a Palworld Dedicated Server on a VPS
Run a persistent Palworld world your friends can join any time. This guide covers official hardware requirements, SteamCMD install, port setup, and the nightly restart that keeps the…
How to Build a Self-Hosted AI Sales Agent for Lead Research and Outreach
The most reliable approach isn't a single autonomous chatbot — it's a workflow system with an LLM in the middle: n8n handles orchestration, Ollama runs the model, and…