NVIDIA DGX-2 integrates 16 NVIDIA V100 Tensor Core GPUs, so you can work with the biggest training datasets.
NVIDIA DGX-2
Break Through the Barriers to AI Speed and Scale
AI Server for the Most Complex AI Challenges
Experience the AI performance of NVIDIA DGX-2™, the world’s first 2 petaFLOPS system integrating 16 NVIDIA V100 Tensor Core GPUs for large-scale AI projects. Powered by NVIDIA DGX software and the scalable architecture of NVIDIA® NVSwitch™, DGX-2 can take on your complex AI challenges.
Discover the Benefits
Exceptional Compute Power
Revolutionary AI Network Fabric
The NVSwitch networking fabric enables greater model parallelism with 2.4 terabytes per second (TB/s) of bisection bandwidth, delivering a 24X increase over prior generations.
AI Scale on a Whole New Level
Build your own private enterprise-grade AI cloud with virtualization support and an architecture purpose-built for scaling.
NVIDIA DGXperts: Integrated Access to AI Expertise
NVIDIA DGXperts are a global team of 14,000+ AI-fluent professionals who have built a wealth of experience over the last decade to help you maximize the value of your DGX investment.
SETTING AI BENCHMARKS
NVIDIA DGX-2 Delivers 195X Faster Deep Learning Training
Explore the Powerful Components of DGX-2
16X FULLY CONNECTED TESLA V100 32GB
0.5 TB total high-bandwidth memory for more complex deep learning models
0.5 TB total high-bandwidth memory for more complex deep learning models
12X NVSWITCHES
Delivering 2.4TB/s bisection bandwidth
Delivering 2.4TB/s bisection bandwidth
8X EDR INFINIBAND/100 GigE
1600Gb/sec total bi-directional bandwidth with low-latency
1600Gb/sec total bi-directional bandwidth with low-latency
NVLINK PLANE CARD
Innovative 2 GPU baseboard interconnect
Innovative 2 GPU baseboard interconnect
2X XEON PLATINUM
Latest Generation CPU for faster, more resilient boot and storage management
Latest Generation CPU for faster, more resilient boot and storage management
1.5TB SYSTEM MEMORY
More system memory to handle larger Deep Learning workloads
More system memory to handle larger Deep Learning workloads
TWO HIGH SPEED ETHERNET NETWORKING CARDS
High I/O throughput for your AI data
High I/O throughput for your AI data
30TB NVME SSDs
Rapidly ingest the largest datasets into cache
Rapidly ingest the largest datasets into cache
Red Hat Enterprise Linux is supported on NVIDIA DGX Systems
See How Customers Are Using NVIDIA DGX-2
DFKI Uses AI for Crisis Management
The German Research Center for Artificial Intelligence (DFKI) is using increased GPU memory and fully connected GPUs based on the NVSwitch architecture in NVIDIA DGX-2 to analyze large-scale satellite and aerial imagery and efficiently dispatch emergency resources.
OSU Accelerates Research and Training
Oregon State University (OSU) uses NVIDIA DGX-2 to accelerate their work in AI, robotics, driverless vehicles, medical imaging, and other research areas.
King’s College London Builds UK’s first AI Platform for Hospitals
NVIDIA DGX-2’s large memory and massive computing power enable specialists to tackle training of large, 3D datasets in minutes instead of days, while keeping the data secure through a federated learning infrastructure.
IIAI Builds an AI Center of Excellence
The Inception Institute of Artificial Intelligence (IIAI) is using NVIDIA DGX-2 to help researchers and engineers accelerate AI research in smart cities and medical imaging.
Learn about enterprise-grade support for NVIDIA DGX systems.