NVIDIA DGX · SUPPLY IN THE EU

NVIDIA DGX,
supplied in Europe

DGX Spark and DGX-class systems on one European contract: hardware, licences and, if you want it, the team that deploys it. Invoiced from Vienna, no import for you to clear.

AVAILABLE TO ORDER
What we supply

Everything below is available to order. We do not publish prices because the configuration, the licences and the term change the number; you get a written quote instead.

SystemMemoryForm factorWhat it is for
DGX Spark128 GB unified, 273 GB/sDesktopA local machine for models that need capacity more than speed. Up to three pair by cable, four through a switch.
DGX-class serversHBM per card, 8-GPU configurationsRackTraining and heavy multi-user inference, where NVLink between cards is the point.
H200 NVL · H100 NVL141 GB · 94 GB HBMPCIe cardAdding DGX-class memory to a server you already have.
NVIDIA AI EnterpriseLicenceThe supported software layer. Included with some systems, separate with others.

All of the above is available to order. Lead time is confirmed with every quote.

JUST THE HARDWARE?

Hardware alone is a fine order

You do not need a project, a licence bundle or an engineering contract to buy from us. One DGX Spark on a desk or a row of DGX-class servers in a rack, any quantity: we quote exactly what you ask for, at a competitive price, invoiced in the EU. The solutions are here when you want them, not a condition of sale.

WHAT COMES WITH IT
Not just a box on a pallet
EU contract and invoice

One counterparty in Vienna. No cross-border purchase to arrange, no import to clear on your side.

Licences sized with the hardware

Where a card needs a licence to do the job you bought it for, it is in the quote, not discovered three months later.

Engineering, if you want it

Our partner Vixen.UNO designs, deploys and supports it. Under the same contract, or not at all – your call.

Warranty and support

Manufacturer warranty handled through us, with support alongside the team who runs the system.

HOW TO CHOOSE
Which one is right for you
Do you actually need 128 GB, or do you need speed?

Most DGX Spark buyers want the memory for 70B-class models. Worth knowing first: a dense 70B in FP8 measured 2.7 tokens per second on 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 →
Will it fit in the rack you have?

A DGX H100 draws up to 10.2 kW. Four of them in one rack is about 41 kW, more than three legacy racks combined. A 400 V 32 A three-phase feed gives you roughly 22 kW, and you plan at 80% of that.

Read the full analysis →
How much memory does your model really want?

Weights are one multiplication. The KV cache is the half that surprises people: a 70B in FP16 at 128K context is 140 GB of weights plus 40 GB of cache, for one user.

Read the full analysis →
FAQ
DGX, in short
Do you sell DGX Spark and DGX servers, or only one of them?
Both, plus the NVL cards that add DGX-class memory to an existing server. Tell us the workload and we will say which of the three actually fits.
Why are there no prices on this page?
Because a DGX number without the configuration, the licences and the term is not a price, it is a guess. You get a written quote with all three, within one business day.
Is NVIDIA AI Enterprise included?
It depends on the system. It is bundled with some and licensed separately with others. Either way it is in the quote, so it is not a surprise later.
Can you deploy it, or only ship it?
Either. Deployment and support come from our engineering partner Vixen.UNO, under the same European contract if you want it that way.
Where does it ship from and who invoices?
Eurokommerz in Vienna invoices you. You have one EU counterparty and no import to handle.
Check price and availability

We reply within one business day

By sending this form you agree that we process your details to answer your enquiry – see our privacy policy.

request@eurokommerz.at  ·  +43 1 585 1405 50  ·  Jordangasse 7, 1010 Vienna