NVIDIA DGX SPARK · SUPPLY IN THE EU

NVIDIA DGX Spark,
supplied in Europe

A 1.2 kg desktop machine with 128 GB of memory that the CPU and the GPU share. It runs models that will not fit on a workstation card, and we are upfront about its speed. Supplied on one European contract, invoiced from Vienna.

Check price and availability Talk to an expert

EU contract and invoice
Licences sized with the hardware
Engineering, if you want it
Warranty and support

AVAILABLE TO ORDER

What is actually in the box

Every figure below is from NVIDIA’s own product page, user guide or quick start guide. We do not publish prices, because configuration and licences change the number; you get a written quote instead.

Specification	DGX Spark	What it means in practice
Superchip	GB10 Grace Blackwell: 20 Arm cores (10 × Cortex-X925, 10 × Cortex-A725) and a Blackwell GPU with 5th-generation Tensor Cores	One chip, not a CPU plus a card. There is no PCIe slot to fill and nothing to configure
Memory	128 GB LPDDR5X, coherent and unified, 256-bit, 273 GB/s	CPU and GPU share one pool. There is no separate VRAM figure to compare with a graphics card
Compute	Up to 1 PFLOP at FP4	NVIDIA’s own footnote says this figure uses the sparsity feature. We found no dense figure from NVIDIA
Storage	1 TB or 4 TB self-encrypting NVMe M.2	Model weights are large. The 4 TB option is the one most people end up wanting
Network	ConnectX-7 with two QSFP ports at 200 Gb/s each, plus 10 GbE RJ-45 and Wi-Fi 7	The QSFP ports are how two or more units are joined, not an afterthought
Power	240 W supply; NVIDIA’s own declaration measures 233.2 W maximum and 38.0 W idle at the wall	It plugs into a desk socket. No rack, no three-phase feed, no room survey
Size and weight	150 × 150 × 50.5 mm, 1.2 kg	About the size of a mini PC. Operating range is 5 to 30 °C
Software	NVIDIA DGX OS, CUDA, the DGX Spark playbooks	The same CUDA you already write for. Arm, so check any binary-only dependency

Available to order, with quantities and lead time confirmed in writing with the quote.

Supplied by Eurokommerz

NVIDIA DGX Spark

Grace Blackwell GB10 · 128 GB unified memory · DGX OS

Check price and availability

On one EU contract and invoice; quantities and lead time confirmed in writing with the quote. We reply within one business day.

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. Two units for two developers, or four for a team: 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.

Check price and availability

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

Is it right for you?

What actually fits in 128 GB

NVIDIA says inference on models up to 200 billion parameters. Do the arithmetic before you plan around it: 200 billion parameters at half a byte each is 100 GB, and 106 to 112 GB with the block scales of MXFP4 or NVFP4, so that claim is a 4-bit claim, and a tight one. In BF16 the same box holds roughly 55 billion. Both are true; they are not the same sentence.

Read the full analysis →

Capacity is real, throughput has a ceiling

Every token has to read the weights through 273 GB/s. LMSYS measured a dense 70B model in FP8 at 2.7 tokens per second for a single user. For a solo developer iterating on prompts that is fine. For twenty people on a chat assistant it is not.

Read the full analysis →

More than two units are supported

The common belief is that Spark tops out at a pair. NVIDIA’s own user guide says up to three connected directly by cable, and up to four through a switch. NVIDIA’s RDMA benchmark measures about 190 Gb/s on a direct 200 GbE link, across the two logical links of one port.

Read the full analysis →

FAQ

DGX Spark, in short

How much of the 128 GB can a model actually use?

NVIDIA publishes no usable-memory figure, and on this platform nvidia-smi cannot report GPU memory use at all. The honest answer comes from NVIDIA’s own playbooks, which default to 0.8 of the pool for vLLM and 0.8 to 0.9 for TensorRT-LLM. Plan on roughly 100 to 115 GB for weights and KV cache together, and leave the rest to the operating system.

Can it really run a 200-billion-parameter model?

Yes, at 4-bit. NVIDIA states inference on models up to 200 billion parameters, and its own validated list includes GPT-OSS-120B and Llama-3.3-70B in 4-bit formats. A 235B mixture-of-experts model is marked multi-node in the same table, which tells you where the single-unit line sits.

What can I fine-tune on one unit?

NVIDIA states up to 70 billion parameters and its fine-tuning playbook shows which method gets there: a full fine-tune on a 3B model, LoRA on 8B, QLoRA on 70B. The scripts are published under those exact names, so the ladder is not our interpretation.

Can I connect more than two?

Up to three directly through QSFP cables, and up to four through a switch, per NVIDIA’s clustering guide. Cable part numbers are specified, so this is a supported configuration rather than a hack.

Is NVIDIA AI Enterprise included?

Not automatically. An entitlement exists only if you bought it, requested an evaluation or received an entitlement certificate. If you need it, we put it in the quote alongside the hardware so it is not a surprise three months later.

Who invoices, and what about warranty?

Eurokommerz in Vienna. One EU counterparty, no import for you to clear, manufacturer warranty handled through us.

RELATED DEEP DIVE