AI VPS
A VPS to run your LLM with Ollama
Keep your prompts, documents and generated answers on French infrastructure: Ollama runs models such as Llama, Phi or Mistral, and Open WebUI adds a chat interface. Our VPSs have no GPU: they suit small quantised models and moderate use.
From €12.99 /month, no commitment
RAM for the model
From 8 GB (VPS Plus) to 32 GB (VPS Titan): the model, its context and its cache must fit in memory without swapping.
CPU inference, no illusions
No GPU: aim for Llama 3.2 3B, a compact Phi variant or Mistral 7B in Q4 with enough RAM.
NVMe for your models
Each model weighs several gigabytes; the guide recommends at least 30 to 50 GB, and the VPS Plus provides 60.
Queries kept in France
Your conversations stay on a VPS hosted in France, as long as you don't enable an external provider.
Recommended plans
Best balance
VPS Plus
The balanced setup for your production apps and panels.
€12.99 /moNo commitment
Order- 4 dedicated vCPUs
- 8 GB DDR4
- 60 GB NVMe
- 500 Mbps network
- Full root access
- 1 dedicated IPv4 address
- noVNC console
- Automatic backup
- Firewall and reverse DNS
Demanding apps
VPS Pro
More memory for databases and resource-hungry applications.
€18.99 /moNo commitment
Order- 4 dedicated vCPUs
- 12 GB DDR4
- 80 GB NVMe
- 500 Mbps network
- Full root access
- 1 dedicated IPv4 address
- noVNC console
- Automatic backup
- Firewall and reverse DNS
- Recommended
Performance
VPS Elite
For running several services side by side on a 1 Gbps network.
€25.99 /moNo commitment
Order- 6 dedicated vCPUs
- 16 GB DDR4
- 100 GB NVMe
- 1 Gbps network
- Full root access
- 1 dedicated IPv4 address
- noVNC console
- Automatic backup
- Firewall and reverse DNS
Heavy workloads
VPS Ultra
For heavy workloads: lots of containers, CI, large websites.
€38.99 /moNo commitment
Order- 8 dedicated vCPUs
- 24 GB DDR4
- 150 GB NVMe
- 1 Gbps network
- Full root access
- 1 dedicated IPv4 address
- noVNC console
- Automatic backup
- Firewall and reverse DNS
Prices in euros, VAT not applicable (article 293 B of the French General Tax Code). Secure payment in the client area, automatic delivery.
How it works
- Order a VPS with enough RAM for your chosen model.
- Install Ollama and download a compact model, keeping port 11434 private.
- Add Open WebUI behind an HTTPS reverse proxy, or connect Ollama to n8n.
Step-by-step guides
Our guides are written in French.
- Héberger un LLM avec Ollama sur un VPSInstallez Ollama sur un VPS pour un petit LLM en self-host : dimensionnement, sécurisation de l'API et connexion à vos apps. Vos données en France.
- Héberger Open WebUI, une interface ChatGPT pour OllamaAjoutez une interface type ChatGPT devant votre LLM local avec Open WebUI : comptes, historique, RAG documents. Une alternative souveraine, en France.
- Créer un agent IA complet avec n8n et OllamaCréez un agent IA 100% auto-hébergé avec n8n et Ollama : webhook, AI Agent, mémoire, outils et actions. Vos données restent sur votre serveur, en France.
French infrastructure, verifiable numbers
- L3/L4Anti-DDoS included
Network attack detection and mitigation on every plan, at no extra cost.
- 3.5 GHzXeon CPU
Intel Xeon Gold 6138 and E5-2673 v4, up to 3.5 GHz turbo for your game servers.
- 100%NVMe storage
No spinning disks. Worlds and databases that respond fast.
- < 15 msto Paris
Infrastructure hosted in France, close to Paris for a low ping.
Frequently asked questions
How much RAM does Ollama need on a VPS?
8 GB is a realistic starting point for a quantised model with 1 to 3 billion parameters (VPS Plus). 16 GB (VPS Elite) is more comfortable and allows some 7B models in Q4. Beyond that, extra RAM adds headroom without guaranteeing good performance on CPU.
Do your VPSs have a GPU?
No, TalCloud does not offer GPU VPSs. Inference runs on CPU: it suits prototyping, a lightly used internal assistant or a low-volume n8n integration, not a busy public chatbot.
Can I get a ChatGPT-style interface?
Yes, with Open WebUI: persistent conversations, user accounts, model selection and RAG over your documents. It installs as a Docker container alongside Ollama, behind an HTTPS reverse proxy.
Should I expose the Ollama API to the internet?
No. The API on port 11434 has no built-in authentication: keep it on 127.0.0.1 or a private Docker network, and go through a reverse proxy with HTTPS and access control if a remote application needs to call it.
Other Linux VPS use cases
- Cheap VPS with dedicated resources
- A VPS for your game servers
- A VPS for Docker and your containers
- A VPS to host n8n and your automations
- Host Nextcloud on your own VPS
- A VPS for your WordPress site
- Host your WooCommerce shop on a VPS
- A VPS for your PrestaShop store
- Your own WireGuard VPN on a VPS
- A VPS to stream your Jellyfin media library
- Host your Vaultwarden vault on a VPS
- A relay VPS for your Home Assistant
- Your own PaaS with Coolify on a VPS
- Host GitLab CE on a VPS built for it
- A VPS for your Odoo Community ERP
- A VPS for your Mailcow mail server
- Host your Immich photo library on a VPS
- Put your Node.js or Python app into production
- An Ubuntu VPS hosted in France
- A Debian VPS, stable and lean
- A VPS to install Pterodactyl and manage your game servers
- A VPS to run your AI agent 24/7