Early this year, NVIDIA announced Project Digits, claiming it to be the world"s smallest AI supercomputer at CES. At GTC 2025, NVIDIA revealed that Project Digits would ship under the DGX Spark branding and began accepting pre-orders for $3,000 USD.
Today, NVIDIA announced that it has started shipping DGX Spark units to pre-order customers and select AI labs around the world. Starting tomorrow, October 15, interested developers will be able to order the DGX Spark on NVIDIA.com. Leading PC OEMs, including Acer, ASUS, Dell Technologies, GIGABYTE, HP, Lenovo, and MSI, will also offer mini supercomputers based on DGX Spark.
In a compact desktop form factor, with system dimensions of 15 cm (L) x 15 cm (W) x 5 cm (H) and a weight of 1.2 kg, the DGX Spark delivers a petaflop of AI performance powered by the NVIDIA GB10 Grace Blackwell Superchip, NVIDIA ConnectX-7 200 Gb/s networking, and NVIDIA NVLink-C2C technology. Thanks to 128 GB of unified memory, developers can run inference on AI models with up to 200 billion parameters and fine-tune models of up to 70 billion parameters entirely locally.
NVIDIA highlighted that leading AI startups and enterprises, including Anaconda, Cadence, ComfyUI, Docker, Google, Hugging Face, JetBrains, LM Studio, Meta, Microsoft, Ollama, and Roboflow, are testing, validating, and optimizing their tools, software, and models for DGX Spark.
Jensen Huang, founder and CEO of NVIDIA, said:
“In 2016, we built DGX-1 to give AI researchers their own supercomputer. I hand-delivered the first system to Elon at a small startup called OpenAI — and from it came ChatGPT, kickstarting the AI revolution. DGX-1 launched the era of AI supercomputers and unlocked the scaling laws that drive modern AI. With DGX Spark, we return to that mission — placing an AI computer in the hands of every developer to ignite the next wave of breakthroughs.”
Apart from the impressive hardware capabilities, the DGX Spark comes preinstalled with the full NVIDIA AI ecosystem, including tools, models, libraries, and NVIDIA NIM microservices, allowing developers to easily get started with AI development with minimal environment setup.