Ollama + Open WebUI VPSYour open AI models, on your own server in France

Ollama is open source software that downloads and runs open AI models. Open WebUI is a web interface that connects to it to chat with those models, manage users and work on your documents. This One Click App deploys both together on your VPS, already connected.

Without a GPU, Ollama computes on the server's processor, which is noticeably slower than a graphics card and slower still as the model grows: plan for small quantised models, from 1 to 14 billion parameters depending on the plan's RAM. On a High performance plan you can attach an NVIDIA L4 GPU with 24 GB of VRAM (€0.70 excl. VAT/hour, billed by the minute, no commitment), which Ollama supports. The One Click App deployment starts Ollama without GPU access: you need to install the NVIDIA driver and the NVIDIA Container Toolkit, then give the GPU to the Ollama service. You can also add an OpenAI-compatible API in Open WebUI.

Without a GPU, the whole model is loaded into the VPS memory, next to Open WebUI and the 1 GB reserved for the system and the One Click Apps platform. The starter model in Ollama's documentation, Gemma 4 E2B, is a 7.2 GB download and Ollama recommends 8 GB of memory for it. Small models fit in 8 GB, 7 to 8 billion parameter models are more comfortable with 16 GB, and the computation runs on the plan's vCPU: that is why this page only offers plans with at least 4 vCPU, 8 GB of RAM and 60 GB of disk.

No model is preinstalled. Once the administrator account is created, type a model name in the Open WebUI model selector (for example llama3.2:3b) or open Admin > Connections: it is downloaded from the Ollama library. Each model has its own licence, shown on its ollama.com page.

With a local Ollama model, no: your questions and the answers are computed on your VPS, in a datacenter in France, and Open WebUI stores the history on the same server. If you add an external API in Open WebUI, the messages sent to that model are processed by its provider.

Once the VPS is created, Ollama and Open WebUI are deployed automatically. Open the application in the One Click Apps section of the console and follow its HTTPS address. Create your account right away: the first account created becomes the administrator. Then add your domain in the Domains tab: the HTTPS certificate is issued automatically.

The application volumes, including the one where Ollama stores downloaded models, are backed up every day at 3 a.m. with 7 days of retention, on the VPS disk: plan your disk space accordingly. These backups protect you from a mistake in the application, not from losing the server: for that, add the VPS backup option (from €2.99 excl. VAT/month) or take a snapshot.

Every night, the console checks whether new Ollama and Open WebUI versions have been published and shows it on the application page. Nothing is updated without your action: one click on "Update" is enough, and the data volumes are kept.

Ollama and Open WebUI are developed by their respective publishers. OnetSolutions provides the server, the deployment and the console tools; configuring the application, choosing models and using them is up to you. Our support covers the VPS: server, network, storage and availability.

No. Ollama is open source under the MIT licence. Open WebUI is free, under the Open WebUI License: a BSD-style licence with a clause that forbids removing the "Open WebUI" branding beyond 50 users over a rolling 30 days, unless the publisher agrees. The prices on this page are those of the VPS.