NVIDIA DGX,
supplied in Europe
DGX Spark on one European contract, and AI servers built to order for the rack: hardware, licences and, if you want it, the team that deploys it. Invoiced from Vienna, no import for you to clear.
- EU contract and invoice
- Licences sized with the hardware
- Engineering, if you want it
- Warranty and support
What we supply
Everything below is available to order; the DGX B300 and the DGX Station GB300 are supplied per project. We do not publish prices because the configuration, the licences and the term change the number; you get a written quote instead.
| System | Memory | Form factor | What it is for |
|---|---|---|---|
| DGX Spark | 128 GB unified, 273 GB/s | Desktop | A local machine for models that need capacity more than speed. Up to three can be linked by cable, four through a switch, and since 21 October 2026 NVIDIA supports clusters of up to eight in manual configuration. |
| DGX Station GB300 · per project | 748 GB coherent: 252 GB HBM3e, 496 GB LPDDR5X | Deskside | One large model on one GPU for a few users, with up to seven MIG instances. Supplied per project as a manufacturer’s version: before we quote, the distribution asks for the company, the project and the intended use. |
| DGX B300 · per project | 2.1 TB HBM3e across 8 GPUs | Rack, 10U | Training and inference on eight Blackwell Ultra GPUs in one NVLink domain. Supplied per project: before we quote, the distribution asks for the company, the project and the intended use. |
| AI servers, built to order | 141 GB HBM3e or 96 GB GDDR7 per card | Rack | Training and multi-user inference on up to eight H200 NVL or RTX PRO 6000 Server Edition cards, sized to your workload. |
| H200 NVL | 141 GB HBM3e | PCIe card | Adding DGX-class memory to a server you already have. |
| NVIDIA AI Enterprise | n/a | Licence | The supported software layer. Included with some systems, separate with others. |
Apart from the DGX B300 and the DGX Station GB300, which are supplied per project, all of the above is available to order, with quantities and lead time confirmed in writing with the quote.
Hardware alone is a fine order
You do not need a project, a licence bundle or an engineering contract to buy from us. DGX Spark for the desk or a rack of AI servers built to order: we quote exactly what you ask for, invoiced in the EU, with quantities and lead time confirmed in writing with the quote. Engineering and licences are optional, not a condition of sale.
Not just a box on a pallet
One counterparty in Vienna. No cross-border purchase to arrange, no import to clear on your side.
Where a card needs a licence to do the job you bought it for, it is in the quote, not discovered three months later.
Our partner Vixen.UNO designs, deploys and supports it. Under the same contract, or not at all. Your call.
Manufacturer warranty handled through us, with support alongside the team who runs the system.
Which one is right for you
Most DGX Spark buyers want the memory for 70B-class models. Worth knowing first: LMSYS measured a dense 70B in FP8 at 2.7 tokens per second for one user, because 70 GB of weights has to be read through 273 GB/s for every single token. The capacity is real. The throughput has a ceiling.
Read the full analysis →A DGX H100 draws up to 10.2 kW. Four of them in one rack is about 41 kW, the load of three to five legacy racks. A 400 V 32 A three-phase feed gives you roughly 22 kW, and you plan at 80% of that.
Read the full analysis →Weights are one multiplication. The KV cache is the half that surprises people: a 70B in FP16 at 128K context is 131 GiB of weights plus 40 GiB of cache, for one user.
Read the full analysis →DGX, in short
Do you sell DGX servers as well as the DGX Spark?
Can we buy a DGX Station GB300 through you?
Why are there no prices on this page?
Is NVIDIA AI Enterprise included?
Can you deploy it, or only ship it?
Where does it ship from and who invoices?
From our engineering blog
Measured token rates, the 273 GB/s ceiling, and the gap between what the slides promise and what owners see.
Read the article →Rack density numbers, the airflow arithmetic and the four checks that decide whether your delivery can be switched on.
Read the article →Weights, KV cache and the overhead you only see in logs: the working formulas.
Read the article →Check price and availability
We reply within one business day