NVIDIA® DGX Station™
AI Workstation for Data Science Teams
The NVIDIA® DGX Station™ brings the incredible performance of an AI supercomputer in a workstation form factor that takes advantage of innovative engineering and a water-cooled system that runs whisper-quiet. The NVIDIA® DGX Station™ packs 500 TeraFLOPS of performance, with the first and only workstation built on four NVIDIA® Tesla® V100 accelerators, including innovations like next generation NVLink™ and new Tensor Core architecture.
This ground-breaking solution offers:
- 3x the performance for deep learning training, compared with today’s fastest GPU workstations
- 100x in speed-up on large data set analysis, compared with a 20 node Spark server cluster
- 5x increase in I/O performance over PCIe-connected GPU’s with NVIDIA® NVLink technology
The DGX Station supports the latest NVIDIA® containersation tools, including docker engine and NVIDIA® drivers which support a complete stack of diverse AI and ML toolsets. The integrated hardware and software stack of the NVIDIA® DGX Station™ means you are up and running in hours, not days. Shorten your time to insight now.
- GPUs: 4X Tesla V100
- TFLOPS (GPU FP16): 480
- GPU Memory: 64 GB total system
- NVIDIA® Tensor Cores: 2,560
- NVIDIA® CUDA® Cores: 20,480
- CPU: Intel® Xeon® E5-2698 v4 2.2 GHz (20-Core)
- System Memory: 256 GB LRDIMM DDR4
Data: 3X 1.92 TB SSD RAID 0
OS: 1X 1.92 TB SSD
- Network: Dual 10 Gb LAN
- Display: 3X DisplayPort, 4K resolution
- Acoustics: < 35 dB
- System Weight: 88 lbs / 40 kg
- System Dimensions:
- Maximum Power Requirements: 1,500 W
- Operating Temperature Range: 10–30 °C
- Software: Ubuntu Desktop Linux OS, DGX Recommended GPU Driver, CUDA Toolkit
Download the full NVIDIA® DGX Station™ datasheet.
This is a regularly stocked item, but only 1 unit is available at this special discounted price.
If we are out of stock, you will be advised of delivery time-frames and asked to confirm your order, before your payment is processed. If you choose to cancel the order at that time, you will not be charged.