PNY Technologies Inc.
  • 5/27/2021
  • PNY

PNY Announces New NVIDIA Ampere Architecture-Based GPUs for Workstations and the Data Center are Available to Order Now

World’s Preeminent Professional Visual, AI, and HPC Accelerated Computing Platform Scales from Desktops to Elastic Hyperconverged Data Centers to the Cloud

PARSIPPANY, NJ - May 27, 2021 – PNY Technologies today announced that the latest NVIDIA GPUs based on the NVIDIA® Ampere architecture — the NVIDIA RTX™ A5000 and NVIDIA RTX A4000 high-performance workstation graphics boards, and the NVIDIA A30, A16 and A10 enterprise-grade data center GPUs — are now available to order from PNY.

Joining the NVIDIA RTX A6000 launched last fall, the NVIDIA RTX A5000 and NVIDIA RTX A4000 high-performance GPUs feature the latest generation of NVIDIA RTX technology including second-generation RT Cores, third-generation Tensor Cores and more efficient CUDA Cores to speed up AI, graphics and real-time rendering. Using these new NVIDIA RTX professional GPUs, artists can create dazzling 3D scenes, architects can iterate on stunning building concepts in real-time, and engineers can create ground-breaking products. GPU memory capacity has been increased by 1.5x (RTX A5000) and 2x (RTX A4000).

Additionally, RTX technology powers NVIDIA Omniverse and NVIDIA Omniverse Enterprise— the only open platform that delivers physically accurate simulation while enabling global collaboration and simulation for complex 3D worlds with real-time ray- and path-traced rendering capabilities.

The NVIDIA A30 and A10 Tensor Core GPUs for the data center feature enhanced Tensor Cores, RT Cores, and CUDA Cores, and the A30 implements Multi-Instance GPU (MIG) technology, allowing enterprises to harness the power of AI to extract new insights from massive datasets, both on premises and in the cloud.

NVIDIA A30 Tensor Cores with Tensor Float (TF32) provide up to 10x higher performance over the NVIDIA T4 with zero code changes and an additional 2x boost with automatic mixed precision and PFP16, delivering a combined 20x throughput increase. When combined with NVIDIA NVLink, PCIe Gen 4, NVIDIA networking, and the NVIDIA Magnum IO SDK, it is possible to scale to thousands of A30 GPUs.

NVIDIA A16 is the ideal GPU for high-density, graphics rich VDI. Based on the latest NVIDIA Ampere architecture, A16 is purpose-built to achieve the highest user density, with up to 64 concurrent users per board in a dual slot form factor. Combined with NVIDIA Virtual PC (vPC) software, it enables the power and performance to tackle any project from anywhere. The NVIDIA A16 provides double the user density and has 4x the encoder throughput of the prior generation to provide the best user experience, and flexibly supports heterogeneous user profiles on a single board.

The NVIDIA A10 provides up to 2.5x more performance than the previous generation T4 for virtual workstations, providing designers, engineers, artists and scientists the power they need to work from anywhere. When combined with NVIDIA virtual GPU (vGPU) software, it can accelerate multiple data center workloads -- from graphics-rich virtual desktops to AI. The combination offers easily managed, secure and flexible infrastructure that can scale to support the quickly changing needs of geographically dispersed teams or remote workforces.

In addition, NVIDIA A10 powered virtual workstations with NVIDIA vGPU software can enable a new era of 3D production when combined with NVIDIA Omniverse for virtual collaboration. Complex creative, design, and engineering visual workflows are transformed as users and teams connect design tools, assets, and projects for collaborative iterations in a virtual world.

“NVIDIA continues to define the future and adoption of RTX professional visual computing with the launch of the NVIDIA RTX A5000 and RTX A4000,” said Steven Kaner, Senior Vice President of Sales and Marketing, PNY. “NVIDIA A30, A16 and A10 allow PNY ecosystem partners to reach into data centers with NVIDIA’s latest products. Implementing AI for better customer engagement, data analytics for forecasting, photorealistic rendering for product innovation, even real-time 3D collaboration for dispersed teams with NVIDIA Omniverse; all are possibilities data center GPUs can realize.”


The new NVIDIA RTX desktop GPUs and NVIDIA data center GPUs are available to order now from PNY Technologies.

For media or customer inquiries, please contact

About PNY Technologies

For over 35 years and thanks to a strong partnership with AI, HPC, and graphics industry leader NVIDIA, PNY has developed a broad and solutions-rich partner ecosystem across NALA that includes graphics, HPC and AI computing, across all major vertical markets. Providing engineers, researchers and visualization clients with cutting-edge NVIDIA professional GPU solutions, PNY understands the needs of its clients, offering pro level technical support and a constant commitment to customer satisfaction. PNY delivers a full spectrum of GPUs and SSD products that enable VDI, HPC and AI environments. Headquartered in Parsippany, New Jersey (USA), PNY maintains facilities in North America, EMEA, India and Asia.