First NVIDIA Professional Graphics Card Packing Ampere Architecture Cores RTX A6000 Announced

NVIDIA’s first-ever professional graphics card, belonging to the next-gen Ampere Architecture, is now official. The NVIDIA RTX A6000 graphics card is also the first SKU to belong to a unified, simplified, and homogenized naming scheme.

A few months ago, NVIDIA announced it will launch two professional products based on Ampere GPUs. The NVIDIA RTX A6000 and A40 would have the GA102 and GA104 graphics processors respectively. These new graphics cards, intended for the professional multimedia content creators and editors, were expected. However, NVIDIA surprised its loyal buyers by ditching the Quadro or Tesla branding altogether for these new Ampere-based professional graphics cards.

NVIDIA RTX A6000 Professional Graphics Card Specifications, and Features:

The NVIDIA RTX A6000 is the only graphics card based on GA102 GPU to feature all CUDA cores enabled. This means the powerful GPU has 10752 CUDA cores. With this power, the GPU has a single-precision compute performance of up to 38.7 TFLOPs. This is 3.1 TLFOPs higher than NVIDIA’s top-end consumer-grade and gaming-centric graphics card, the NVIDIA GeForce RTX 3090.

At 48 GB, the NVIDIA RTX A6000 features twice the memory capacity of the RTX 3090. Incidentally, such high-density memory modules are GDDR6, and not GDDR6X yet. Hence the total memory bandwidth available for the RTX A6000 is slightly lower.

The NVIDIA RTX A6000 features four DisplayPort 1.4 connectors. However, it lacks HDMI 2.1 output. Only two RTX A6000 cards can be connected through a new low-profile NVLink bridge. Incidentally, this workstation card also supports NVIDIA vGPU virtualization technologies.

The graphics card is currently listed in NVIDIA’s own store at 4,650 USD. Needless to mention, the asking price is quite lower than NVIDIA RTX A6000 based on Turing architecture.

NVIDIA Renames Quadro Drivers into NVIDIA RTX Enterprise Drivers:

NVIDIA has officially discontinued its Quadro and Tesla, naming series. Henceforth it will offer a single series of products under the branding NVIDIA RTX Axx or NVIDIA Axx. Moving ahead, the RTX branding will matter because these cards will replace the Quadro series. Meanwhile, the non-RTX A40 card is essentially a Tesla successor that will accompany the already launched GA100 A100 accelerator.

In accordance with the change in branding, NVIDIA also announced it will rename its Quadro drivers into NVIDIA RTX Enterprise driver. This was an obvious change as NVIDIA has already discontinued the Quadro products series in favor of its RTX-branded accelerators and workstation solutions.

Besides the name change, nothing else will alter, confirmed NVIDIA. It is obvious the company was referring to its commitment to offering enterprise-class quality, reliability, performance, and security. Incidentally, the driver branch name will also transition from “Optimal Driver for Enterprise” to “Production Branch.” The new branch name will now allow driver types to be consistently referenced across other enterprise GPU products as well, such as Data Center GPUs.

Alap Naik Desai

A B.Tech Plastics (UDCT) and a Windows enthusiast. Optimizing the OS, exploring software, searching and deploying solutions to strange and weird issues is Alap's main interest.