Four thousand nine hundred and ninety-nine dollars. That is the price of a high-end laptop, and from 23 October it is the price of a machine that, per NVIDIA, runs a 100-billion-parameter model on your desk without sending anything out.
Fact
The facts: on 2 October 2026 NVIDIA announced DGX Spark 64GB: a configuration with the GB10 Grace Blackwell Superchip and 64 GB of unified memory, from $4,999, on sale from Friday, 23 October 2026 at Acer, ASUS, Dell, Gigabyte, HP and MSI. NVIDIA Sync Cluster Assistant detects two connected units, validates the configuration and configures the network: they connect directly with a QSFP cable over the built-in ConnectX-7 at 200 GbE, and the memory pools to 128 GB. Per NVIDIA, one machine runs models of up to 100 billion parameters, two run up to 200 billion, and two clustered systems deliver up to 1.7x the performance of one, measured with Qwen 3.8 27B. Software: NVIDIA Agent Toolkit, the CUDA-X libraries, the open Nemotron models, with Ollama, vLLM and PyTorch with CUDA working out of the box.
The numbers are NVIDIA's and were measured on one model, Qwen 3.8 27B. With another model and another workload they will differ. 1.7x from two machines means the cable eats about 15 percent. Normal for a link between two boxes, and better than I expected from a cable on a desk.
The important part is further down: who it is for. A studio of ten, a law office, a medical practice. Anyone who wants a model over their own documents and does not want the documents to leave the room. Until now that meant either the cloud or a server with a rack and air conditioning. Now it is a box on the desk, and a second box if needed.
The cloud sells memory by the hour. Here you buy it once.
What NVIDIA does not say: how fast a 200-billion model answers on two of these. "Runs" and "runs nicely" are different words. We find out on 23 October, when someone puts it on a desk and loads their own model, not the benchmark.
Official primary sources
NVIDIA - NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI, 02.10.2026The visual is generated code-art, no third-party images.