DGX Spark: What the Hardware Actually Is
DGX Spark is a small box whose whole reason to exist is memory: 128 GB that the CPU and the GPU both address directly. Understanding why that matters tells you more than the petaFLOP figure does.
The hardware, plainly
The DGX Spark is a desktop box with one main chip in it. That chip, the GB10 Grace Blackwell Superchip, was co-designed with MediaTek and puts a 20-core Arm CPU, 10 Cortex-X925 and 10 Cortex-A725, next to a Blackwell GPU with 6,144 CUDA cores and fifth-generation tensor cores. The CPU and GPU share 128 GB of LPDDR5x memory through a coherent interconnect, so a program on the CPU can point at the same bytes the GPU is using, with no copy in between.
It was shown as Project DIGITS at CES on 6 January 2025 with a $3,000 price and a May release date, renamed DGX Spark at GTC on 18 March 2025, and shipped on 15 October 2025 at $3,999 for the 4 TB version. A 64 GB version sold through OEM partners came later. It uses a 240 W power supply, the chip itself is rated at 140 W, and the whole unit is 150 mm square and weighs 1.2 kg.
Why memory, not FLOPs, decides what you can run
The headline number is up to 1 petaFLOP of FP4 performance, and it is a theoretical figure that assumes 4-bit numbers and sparsity. The number that decides your daily experience is 273 GB/s of memory bandwidth. Every token the model generates needs the weights read from memory, so tokens per second is set by how fast those bytes arrive, not by how many multiply-adds the tensor cores can perform.
That is why the box is described as a capacity machine rather than a speed machine. Reviews of a 120B-parameter open model on a Spark report around 35 to 40 tokens per second, and one unit can hold roughly 200B parameters at 4-bit in its 128 GB, or about 405B with two units linked over the 200 Gbps ConnectX port. For a school the capacity is the argument: a model that fits entirely in memory, with no request leaving the building and no usage fee.
Step by step
-
Separate the two numbers before you buy
Capacity is the 128 GB of shared memory. Speed is the 273 GB/s bandwidth and the tokens per second you actually get. Quoting the petaFLOP figure to a parent instead of the bandwidth figure is the most common mistake in this conversation.
-
Work out what fits
At 4-bit, budget about 0.7 GB per billion parameters, so 128 GB of shared memory holds a model of roughly 180 to 200 billion parameters, with room left for the context and the operating system.
-
Check the power and the heat
The chip is rated at 140 W with a 240 W supply, and a box that size needs airflow around it. In a lab with 20 of them, the power and cooling budget is a bigger number than the purchase price.
-
Budget the price honestly
It launched at $3,999 for 4 TB, a 64 GB version appeared around $3,150 excluding VAT through OEM channels in late 2026, and NVIDIA's own marketplace listing for the 4 TB unit shows $6,950. Prices and stock move, so check the verified retail price rather than the launch figure.
-
Decide what the classroom uses it for
Local inference, fine-tuning a small model on your own data, and dataset work are realistic. Training a large model from scratch is not, and a petaFLOP figure will not change that.
-
Pair it with a microcontroller
Use the Spark for the slow, fuzzy decisions and an Arduino or Mega for the millisecond loop. That split is the one you would design on a factory floor, and it is the part students can actually build.
What you'll need
| Item | Qty | Why |
|---|---|---|
| NVIDIA DGX Spark | 1 | The 128 GB unified-memory box. Choose the 64 GB or 128 GB version based on the model size you actually need, not on the headline. |
| Monitor with USB-C or USB-C to HDMI adapter | 1 | The unit has one HDMI 2.1a and up to three DisplayPort over USB-C, so check what the classroom already has before ordering. |
| Arduino Mega 2560 | 1 | Handles the sensors and the real-time control, and has the extra serial ports for logging sensor data to the Spark. |
| HC-SR04 ultrasonic sensor | 1 | The observation the model reasons about before the decision comes back over serial. |
| LED bar graph module | 1 | Shows the model's decision as a number you can check rather than a word you have to trust. |
| 10 GbE network cable | 1 | The Spark has 10 GbE and a ConnectX-7 port at 200 Gbps, which is how two units share one large model. |
Practise it before you build it
Every step above has a matching circuit in the ThinkEdge Learn simulator. The simulator runs a real
Arduino sketch against a modified-nodal-analysis solver, so digitalWrite actually drives the
LED on screen and the readings change when you change the wiring — no hardware, no burnt components.
The Mega has 4 hardware serial ports (Serial, Serial1, Serial2, Serial3). That means you can talk to 4 different devices at the SAME time — like a GPS, a Bluetooth module, an XBee radio, and the USB. Use 3 of those ports to read 3 different sensors in parallel and stream their data to the Serial Monitor as a CSV row every second. This is the foundation of every real Arduino data logger.
A 10-segment LED bar graph is the easiest way to visualize an analog input: spin a potentiometer and 1, 2, 3 ... 10 LEDs light up in sequence. This is a "VU meter" — the kind you see on stereo equipment. The Mega is ideal because it has 10 free digital pins without stealing any from the analog or serial pins. The same code can be extended to 20, 30, or 100 LEDs on a Mega.
Mount an HC-SR04 ultrasonic sensor on top of a servo. Sweep the servo from 0° to 180° and back, and at each step measure the distance. Print the results to the Serial Monitor as "angle,distance" pairs. Open the Serial Plotter in the Arduino IDE to see a live radar-like graph of the room. With Processing on your computer, you can build a full visual radar.
Real smart fans use TWO sensors: temperature (to know WHEN to turn on) and motion or distance (to know IF someone is present). If it's hot AND someone is within 100 cm, the fan turns on. This avoids the silly situation of a fan blowing in an empty room. We use the DHT11 for temperature, the ultrasonic for distance, and a real DC fan motor for the output.
A real Arduino project almost always involves a sensor + a way to see the data. The DHT11 reads temperature and humidity, and the Serial Monitor (the window in the Arduino IDE) shows the readings. The Nano is perfect for this because it plugs directly into a breadboard with no extra wiring for power — you can build a complete data logger in 5 minutes.
A real traffic light runs a state machine: GREEN (cars go) → YELLOW (slow down) → RED (cars stop) → PEDESTRIAN WALK (cross the road) → RED → GREEN. The Mega has enough pins to build a full intersection: 3 LEDs for cars in one direction, 3 LEDs for cars in the other, 2 LEDs for the pedestrian signal, and a button to request to cross. Use millis() for non-blocking timing so the button check is responsive.
Common questions
Is DGX Spark worth it for a school lab?
For most schools, no. It launched at $3,999 and, even at the 64 GB size, it is still several thousand dollars for hardware that most class projects never approach. A used workstation with 24 GB of graphics memory, or even a shared cloud credit, will carry a school project further for a fraction of the cost. The case for the Spark is capacity and privacy: a large model resident in memory, running on a machine inside your building.
Can a DGX Spark replace a data centre?
No, and the difference is worth teaching. A Spark has one chip and a few hundred gigabytes per second of bandwidth. A training cluster has thousands of graphics processors linked together. What a Spark can do that a laptop cannot is hold a model of a few hundred billion parameters in memory and serve it locally, which is a genuine capability for a lab, just a narrow one.
How fast is it in practice?
Around 35 to 40 tokens per second for a 120B-parameter class model running locally on a 273 GB/s memory bus. Since generation is bound by reading the model weights, a smaller model is not automatically faster, and the software releases since launch have improved throughput noticeably. Benchmark the model you intend to run, not the headline figure.
Related guides
Try the full simulator with your class
103 guided circuit projects, 21 lessons and an in-browser Arduino simulator. The first 15 projects are free, no account needed. NCERT Science mapping on 47 projects, with Arabic and English copy in the regional builds.