NVMe storage, free SSL, daily backups and engineers on call around the clock.
See all hosting plansBare-metal servers with 5 IPv4 addresses each, from Xeon to Ryzen 9.
Compare dedicated servers256-bit encryption, wide browser recognition and free reissues on every certificate.
Compare certificatesRun projects on your own domain with your logo, client roles and daily backups.
See workspace plansCall, email or open a ticket at any hour.
Host Llama, Mistral, Qwen and other open models for chat, search and automation. Your prompts and documents stay on your own server instead of a third-party API.
AI servers from €8.94 / month
Question: What notice period do our supplier contracts require for renewal?
Popular open-weight model families that run with tools such as Ollama, llama.cpp or vLLM. Check each model’s licence for commercial use.
1B, 3B, 8B, 70B
General chat, summaries and agents
7B, 8x7B, 24B
Fast assistants and European languages
0.5B to 72B
Multilingual work and coding
2B, 9B, 27B
Compact models for focused tasks
3.8B, 14B
Small models that reason well
1.5B to 70B
Step-by-step reasoning
Under 1B
Search and retrieval over your documents
Up to 1.5B
Speech to text, kept private
With a public AI API, every prompt and every document you send is processed on someone else’s infrastructure. On your own server, the model, the data and the logs all live in one place you control.
Public AI API
Your own server
Pick a model size and precision. We estimate the memory it needs and list servers from our catalog that can hold it.
Rule of thumb: parameters × bytes per parameter, plus about 20% and a little room for the conversation context. Leave extra memory for your application and operating system.
Memory needed, roughly
7 GB
Servers in our catalog with enough memory, with headroom where possible:
Servers listed are from our current catalog and run models on CPU. For GPU servers, ask our team.
Servers prepared for running open models.
4 vCPU Cores, 6GB RAM DDR4
6 vCPU Cores, 16GB RAM DDR4
8 vCPU Cores, 24GB RAM DDR4
Prompts, documents and outputs are processed and stored on your server only.
Servers in our catalog go up to 256GB of RAM, enough for large quantised models.
Install Ollama, llama.cpp, vLLM, Open WebUI or your own stack.
Tools like Ollama and vLLM expose an API your existing code can call with a URL change.
Connect models to n8n workflows, internal tools and databases on the same server.
A monthly server price instead of a bill that grows with every token.
Run embeddings and a vector database next to the model for retrieval over your files.
Help choosing a model and server size, by phone, email, WhatsApp and ticket, around the clock.
Planning something specific? Our team can size a server with you.
Tell us the model you want to run and we will recommend a server sized for it.
