Custom configured, quickly delivered!
Your shopping cart is empty
Buy Online or Call 800-237-0402
Search
The NVIDIA Quadro GV100 graphics card with Volta architecture brings a lot of capabilities to deep learning and simulation for designers, engineers, and scientists. This GPU is equipped with 32GB of high-bandwidth memory capacity and the ability to scale two GPUs with NVIDIA NVLink. Offering 5120 CUDA parallel processing cores and up to 118.5 TFLOPS for deep learning performance, it can handle large data sets and enable the future of AI and simulation workflows.
The NVIDIA Quadro GV100 is the successor to the Quadro GP100 and marks the introduction of the Volta architecture into the Quadro family. The GPU meets the demands of next-generation ray tracing, AI, simulation, and VR enhanced workflows that designers and scientists need.
Under the hood, the Quadro GV100 is based on a 12nm manufacturing process packing 5120 CUDA cores on a single chip with about 21,100 million transistors. The GPU also includes up to 640 Tensor cores, 320 texture mapping units, and 128 ROPs to improve the speed of machine learning applications. With all of this power, users can connect up to four monitors with high resolution.
The Quadro GV100 is designed with 32GB of high-bandwidth memory capacity, which uses a 4096-bit bus for 870GB/sec of memory bandwidth. There’s also an opportunity to scale two GV100s for up to 64GB of HBM2 memory with NVIDIA NVLink. By combining two GV100 graphics cards, users are able to see a substantial performance increase in a single workstation chassis.
The NVIDIA GV100 GPU has two NVLink connectors to enjoy the full benefits of low latency data transfers, remote memory access, and memory pooling. The GPU now has a 4x DisplayPort 1.4 setup, dropping the GP100’s sole DVI port. As a dual-slot card, the NVIDIA Quadro GV100 draws power from an 8-pin power connector with up to 250W of power, an increase from the GP100’s 235W.
The NVIDIA Quadro GV100 GPU features many upgrades compared to its predecessor, the GP100. With Volta architecture, 5120 CUDA cores, and support for two GV100’s with up to 64GB of HBM2 memory combined, the processing power on this unit can accelerate workloads for a noticeable performance increase.
If you know what you want but can't find the exact configuration you're looking for, have one of our knowledgeable sales staff contact you. Give us a list of the components you would like to incorporate into the system, and the quantities, if more than one. We will get back to you immediately with an official quote.