NVIDIA Quadro GV100
NVIDIA Quadro GV100
Part No. VCQGV100-PB
EAN: 3536403363345

NVIDIA Quadro® GV100: Reinventing the Workstation for AI
The Power To Accelerate AI-Enhanced Workflows

The NVIDIA Quadro® GV100 is reinventing the workstation to meet the demands of AI-enhanced design and visualization workflows. It’s powered by NVDIA Volta, delivering the extreme 32 GB HBM2 memory capacity, scalability, and performance that designers, architects, and scientists need to create, build, and solve the impossible.
Support for the NVIDIA GPU Cloud (NGC), Deep Learning SDK and many widely used deep learning frameworks puts the power of deep learning training and high-performance GPU-accelerated algorithm development tools in the hands of professional users and software developers.
The Quadro GV100 can run FEA, CFD, CEM, and other GPU-accelerated analysis codes faster. 32 GB of HBM memory means that larger simulations will fit into memory compared to the Quadro GP100. Users can connect two GV100 cards with NVLink to provide 64 GB of HBM memory and run the largest simulations.

NVIDIA CUDA Cores5120
NVIDIA Tensor Cores640
GPU Memory32GB HBM2
Memory Interface4096-bit
Memory BandwidthUp to 870 GB/s
Display Connectors4 x DP 1.4
DisplayPort 1.4Yes
Warranty3 Years
PNY Part NumberVCQGV100-PB
EAN Number3536403363345

PNY Technologies delivers professional graphics cards with all necessary accessories, including appropriate adapters, cables, brackets, software installation disc and documentation to ensure a quick and successful install. PNY Technologies offers a standard 3-year warranty, dedicated Quadro Field Application engineers and direct tech support hot lines for pre- and post-support.

QUADRO GV100 – Product Specifications
 
Memory Size32 GB HBM2
Memory Interface4096-bit
Memory BandwidthUp to 870 GB/s
ECCYes
NVIDIA CUDA Cores5120
NVIDIA Tensor Cores640
Double-Precision Performance7.4 TFLOPS
Single-Precision Performance14.8 TFLOPS
Tensor Performance118.5 TFLOPS
NVIDIA NVLinkConnects 2 Quadro GV100 GPUs
NVIDIA NVLink bandwidth200 GB/s
System InterfacePCI Express 3.0 x 16
Max Power Consumption 250 W
Thermal SolutionActive
Form Factor4.4” H x 10.5” L, Dual Slot,
Full Height
Display Connectors4 x DP 1.4
Max Simultaneous Displays4 direct DP 1.4
Display Resolution4x 4096×2160 @ 120 Hz
4x 5120×2880 @ 60 Hz
2x 7680×4320 @ 60 Hz
VR ReadyYes
Graphics APIsShader Model 5.1, OpenGL 4.5, DirectX 12, Vulkan 1.0
Compute APIsCUDA,  DirectCompute, OpenCL™
DisplayPort with AudioYes
NVIDIA nView™ Desktop 
Management Software Compatibility
Yes
Mosaic ModeYes
3D Stereo SupportYes
NVIDIA GPUDirect™ SupportYes
Quadro Sync II CompatibilityYes
Stereo ConnectorYes
Package Content

4 × DP to DVI (SL) Adapters
1 × DP to HDMI Adapter 
1 × Stereo Connector Bracket

1 × Quick Installation Guide
1 × Power Adapter 8-pin to dual 6-pin 

  
QUADRO GV100 – Minimum System Requirements
 
Windows 10, Windows 8.1, Windows 8, 7, Linux, or Solaris
PCIe x16 expansion slot
1GB or more of system memory, 2GB recommended
200MB of available disk space for full driver installation
Blu-ray or DVD-ROM drive
Internet connection (if preferred for driver installation)
DisplayPort, DVI, or VGA compatible display(s)
 
QUADRO GV100 – SKUs and EANs 
    
RetailUnit

VCQGV100-PB

EAN: 3536403363345

NVIDIA Quadro® GV100: Reinventing the Workstation for AI
The Power To Accelerate AI-Enhanced Workflows

The NVIDIA Quadro® GV100 is reinventing the workstation to meet the demands of AI-enhanced design and visualization workflows. It’s powered by NVDIA Volta, delivering the extreme 32 GB HBM2 memory capacity, scalability, and performance that designers, architects, and scientists need to create, build, and solve the impossible.
Support for the NVIDIA GPU Cloud (NGC), Deep Learning SDK and many widely used deep learning frameworks puts the power of deep learning training and high-performance GPU-accelerated algorithm development tools in the hands of professional users and software developers.
The Quadro GV100 can run FEA, CFD, CEM, and other GPU-accelerated analysis codes faster. 32 GB of HBM memory means that larger simulations will fit into memory compared to the Quadro GP100. Users can connect two GV100 cards with NVLink to provide 64 GB of HBM memory and run the largest simulations.