NVIDIA 900-2H403-0000-000 Tesla P100 SXM2 Graphic Card - 16 GB HBM2

MPN: 900-2H403-0000-000
NVIDIA 900-2H403-0000-000 Tesla P100 SXM2 Graphic Card - 16 GB HBM2
Out of Stock
Highlights
  • Standard Memory: 16 GB
  • Host Interface: AGP
  • Cooler Type: Passive Cooler
  • Product Type: Graphic Card
$8,002.50
Please log in to add an item to your wishlist.
Non-cancelable and non-returnable
B2B pricing options available.

SabrePC B2B Account Services

Save instantly and shop with assurance knowing that you have a dedicated account team a phone call or email away to help answer any of your questions with a B2B account.

  • Business-Only Pricing
  • Personalized Quotes
  • Fast Delivery
  • Products and Support
Need Help? Let's talk about it.
Please log in to add an item to your wishlist.
NVIDIA 900-2H403-0000-000 Tesla P100 SXM2 Graphic Card - 16 GB HBM2
MPN: 900-2H403-0000-000

$8,002.50

Non-cancelable and non-returnable

NVIDIA 900-2H403-0000-000 Tesla P100 SXM2 Graphic Card - 16 GB HBM2

Out of Stock
Highlights
  • Standard Memory: 16 GB
  • Host Interface: AGP
  • Cooler Type: Passive Cooler
  • Product Type: Graphic Card
Infinite compute power for the modern data center

Artificial intelligence for self-driving cars. Predicting our climate's future. A new drug to treat cancer. The world's most important challenges require tremendous amounts of computing to become reality. But today's data centers rely on many interconnected commodity compute nodes, limiting the performance needed to drive important HPC and hyperscale workloads.

The NVIDIA Tesla P100 is the most advanced data center accelerator ever built, leveraging the groundbreaking NVIDIA Pascalâ„¢ GPU architecture to deliver the world's fastest compute node. It's powered by four innovative technologies with huge jumps in performance for HPC and deep learning workloads.

The Tesla P100 also features NVIDIA NVLinkâ„¢ technology that enables superior strong-scaling performance for HPC and hyperscale applications. Up to eight Tesla P100 GPUs interconnected in a single node can deliver the performance of racks of commodity CPU servers.