Katarzyna Petru
NVIDIA has just begun the global shipping of DGX Spark – the smallest AI supercomputer in the company's history. The system is designed to give artificial intelligence creators local server-class computing power, packed in a desktop format. In practice, this means 1 PFLOP of computing power and 128 GB of unified memory, allowing the running of models with up to 200 billion parameters without the need for cloud access.
The launch was not without symbolism – Jensen Huang, CEO of NVIDIA, personally delivered the first unit to Elon Musk at SpaceX, referencing 2016, when the same duo picked up the first DGX-1 system, from which ChatGPT was later born.
“In 2016, the DGX-1 gave scientists their own supercomputer. Now the DGX Spark is set to put AI in the hands of every developer” – said Jensen Huang.
AI power in a desktop format
The new DGX Spark is built on the Grace Blackwell architecture and equipped with the GB10 Superchip, which combines GPU and CPU with a bandwidth that is 5 times greater than PCIe 5.0. The entire system consumes just 240 W of power, weighs 1.2 kg, yet offers petascale data processing.
The package includes a complete NVIDIA AI Stack environment – CUDA, NVLink-C2C, ConnectX-7 (200 Gb/s), libraries, models, and microservices NVIDIA NIM, allowing AI projects to be launched immediately after unpacking the hardware.
The first units are going to partners such as Acer, ASUS, Dell, Lenovo, MSI, HP, GIGABYTE, as well as to Anaconda, Meta, Microsoft, Hugging Face, and JetBrains. NVIDIA announces that DGX Spark will become the new standard in creating AI agents and physical models, including in local applications.
Comparison: from DGX-1 to DGX Spark
Specification | DGX-1 (2016) | DGX Spark (2025) |
|---|---|---|
GPU Architecture | NVIDIA Pascal | NVIDIA Blackwell |
GPU Memory | 128 GB (16 GB per GPU) | 128 GB unified system memory |
AI Performance | 170 TFLOPS (FP16) | 1 PFLOP (FP4) |
Power Consumption | 3200 W | 240 W |
Dimensions | 866 × 444 × 131 mm | 150 × 150 × 50.5 mm |
Weight | 60.8 kg | 1.2 kg |
Price | 129,000 USD | 3,999 USD |
A New Era for AI Creators
Thanks to Spark, developers can locally train and fine-tune models with up to 70 billion parameters, create AI agents, tools for computer vision, or personalized chatbots optimized for Grace Blackwell. The system is fully ready to work with models such as FLUX.1, Qwen3, or Cosmos Reason.
As Professor Kyunghyun Cho from NYU Global AI Frontier Lab put it:
“DGX Spark gives us petascale power on the desk. It’s a completely new way of conducting AI research — even in sensitive areas such as medicine.”
Starting from October 15, the DGX Spark can be ordered at NVIDIA.com, and partners such as Acer, ASUS, Dell, HP, Lenovo, and MSI are offering their own versions of this computer. It will also appear in the Micro Center network in the USA, and global distribution will begin in the coming weeks.
