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.
- EU contract and invoice
- Licences sized with the hardware
- Engineering, if you want it
- Warranty and support
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 We do not publish prices, because configuration and licences change the number; you get a written quote instead.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. NVIDIA also lists a 64 GB configuration, sold only through OEM partners; the Founders Edition we supply has 128 GB |
| Compute | Up to 1 PFLOP at FP4 | NVIDIA’s datasheet footnote says this figure uses the sparsity feature. We found no dense figure from NVIDIA |
| Storage | 4 TB self-encrypting NVMe M.2 (Founders Edition) | Model weights are large. Partner GB10 systems also come with 1 or 2 TB |
| 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 Sparks 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.
Hardware alone is a fine order
You do not need a project, a licence bundle or an engineering contract to buy from us. Two Sparks 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.
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.
Is it right for you?
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 →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 →A common assumption is that no more than two Sparks can be linked. NVIDIA’s own user guide says up to three connected directly by cable, and up to four through a switch; since 21 October 2026 NVIDIA also supports clusters of up to eight Sparks in manual configuration (NVIDIA blog of that date). 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 →DGX Spark, in short
How much of the 128 GB can a model actually use?
Can it really run a 200-billion-parameter model?
What can I fine-tune on one Spark?
Can I connect more than two?
Is NVIDIA AI Enterprise included?
Who invoices, and what about warranty?
From our engineering blog
The arithmetic behind the 200B claim, what each precision costs, and what you can fine-tune on one Spark.
Read the article →Measured token rates, the 273 GB/s ceiling, and the gap between the slides and what owners see.
Read the article →Three ways to start, and the four questions that decide which one is yours.
Read the article →Check price and availability
We reply within one business day