NVIDIA GP100 graphics card 16 GB HBM2

Professional compute card

The NVIDIA Quadro GP100 is a full-height graphics card built for professional visualization and simulation workloads. It targets engineers, researchers and developers who need high double-precision throughput and large memory capacity for CAE, rendering and deep-learning tasks.

PCI Express 3.0 x16 interface

The board installs in a standard PCI Express 3.0 x16 slot and draws power from the motherboard and auxiliary connectors. Four DisplayPort outputs drive multiple 3D stereo displays while NVLink allows two GP100 cards to be bridged for shared memory scaling. GPU Direct enables fast data paths to storage and network adapters.

16 GB HBM2 with 4096-bit bus

Sixteen gigabytes of HBM2 memory on a 4096-bit bus deliver the bandwidth needed for large models and datasets. The GPU provides 3580 FP32 and 1792 FP64 CUDA cores for compute-intensive workloads. FP16 performance supports AI training workflows, while the fixed memory capacity sets the upper limit for single-board problem sizes.