Groundbreaking AI, At Your Desk

Designed for your office, NVIDIA® DGX Station™ is the world’s first personal supercomputer for leading-edge AI development. Built on the same NVIDIA GPU Cloud Deep Learning Stack powering all NVIDIA DGX™ Systems, you can now experiment at your desk and extend your work across DGX Systems and the cloud.

 

The Making of NVIDIA DGX Station
Get an inside look into how this deep learning workstation was
purposefully designed for developers and researchers.

World Class Computing Performance in the Hands of Your Teams Get the Fastest Start in Data Science and AI Research No Data Center? No Problem. Access to AI Expertise and Enterprise Grade Support
DGX Station is the only workstation with four NVIDIA® Tesla® V100 Tensor Core GPUs, integrated with a fully-connected four-way NVLink™ architecture, delivering 500 teraFLOPS of AI power, equivalent to hundreds of servers, enabling your entire team to experiment faster, iterate frequently, with effortless productivity. Don’t lose weeks or months integrating hardware and software to set up your AI platform. DGX Station includes a full stack optimized hardware and software solution that lets your data science teams get started within only an hour. Need to deliver AI breakthroughs but lack the data center to develop them? Whisper quiet and water-cooled, DGX Station has the computing capacity of a data center in an office-friendly package. Innovate on your terms instead of waiting for compute cycles in the data center. Keep your experiments running and your team productive. With NVIDIA DGX Station, you get access to AI expertise, a library of expert training, software upgrades and updates, and a single contact support for priority resolution of your issues.

Accelerate Data Science Discovery with NVIDIA DGX Station

Deliver breakthrough performance for data science and machine learning workflows with RAPIDS and NVIDIA DGX Station. Optimized for accelerated data loading, data manipulation, and training of algorithms, get faster insights leveraging the performance and large GPU memory footprint of NVIDIA DGX Station.

1 – 1/20TH THE POWER
CONSUMPTION
2 – 2ND GENERATION
NVIDIA NVLINK
3 – THREE
DISPLAYPORTS
One DGX Station has the computer capacity of four
racks of servers, and requires much less power.
High-speed interconnect 200GB/s per GPU, 5X faster
than current PCIe gen3x16 interconnections.
All fully supporting 4K monitor resolution
4 – NVIDIA TESLA V100 5- INTEL XEON CP 6-WATER COOLING
The most advenced AI GPU ever built, optimized for
deep learning with Tensor Core architecture, now
with 32GB of memory
Optimized for boot, storage management, and deep learning framework coordination
itecture, now
with 32GB of memory
Design to be whisper quiet, making it a perfect
addition to your desk while still being optimized for performance