NVIDIA today introduced its personal AI supercomputers, DGX Spark and DGX Station, powered by the NVIDIA Grace Blackwell platform. These systems are designed to enable AI developers, researchers, data scientists, and students to prototype, fine-tune, and infer large models on desktops.
DGX Spark is the world’s smallest AI supercomputer, featuring the NVIDIA GB10 Grace Blackwell Superchip with a powerful GPU and fifth-generation Tensor Cores. This allows for massive performance and capabilities in generative and physical AI applications.
DGX Station, a new high-performance desktop supercomputer, also runs on the NVIDIA Blackwell Ultra platform and features 784GB of coherent memory space to accelerate large-scale training and inferencing workloads. It is expected to be available from manufacturing partners later this year.
The systems are designed to provide seamless movement between local desktops and accelerated cloud or data center infrastructure, with minimal code changes required. NVIDIA’s full-stack AI platform also enables users to deploy models on DGX Cloud or other infrastructure, making it easier to prototype, fine-tune, and iterate on workflows.
Jensen Huang, founder and CEO of NVIDIA, stated that AI has transformed every layer of the computing stack, leading to the emergence of new computers designed for AI-native developers. The introduction of DGX Spark and DGX Station marks a significant step forward in enabling AI applications across desktops, cloud services, and edge devices.
Reservations for DGX Spark systems are now open, while DGX Station is expected to be available later this year from manufacturing partners such as ASUS, Dell, HP Inc., and Lenovo.
Source: https://nvidianews.nvidia.com/news/nvidia-announces-dgx-spark-and-dgx-station-personal-ai-computers