NVIDIA now has a solution for professionals eager to get their hands on its new Ampere architecture: the RTX A6000 and A40. They’re two power-house cards that easily outclass the drool-worthy $1,499 RTX 3090, with 10,752 CUDA cores and 48GB of VRAM. And yes, in case you were wondering, they’re the successors to the previous RTX 8000 and 6000 Quadro GPUs. It’s unclear why NVIDIA is dropping the Quadro branding this time around, but the name on the card won’t matter to anyone demanding professional-grade performance.
NVIDIA isn’t divulging clock speeds and specific technical details about these cards just yet, but you can think of them as super-powered version of the RTX 3080 and 3090. They’re running the same fully GA102 GPU as those two cards, and they’re otherwise identical to each other, except the A90 is completely passively cooled and has a slower 14.5 Gbps memory clock. They’re also running slower GDDR6 RAM, compared to the faster GDDR6X on the consumer cards, so there may be some strange performance disparities between the 3080 and 3090, as Anandtech points out. The company says the A6000 is around twice as fast as the RTX 8000 in some cases.
As usual, these aren’t cards many consumers will need to consider, but they’re compelling options for anyone who needs GPU power for professional work. The A90 will be a solid choice for dense compute-focused servers. NVIDIA also includes three DisplayPort connections, whereas previous passively cooled cards were meant for head-less compute tasks. The company says the RTX A6000 will be available in mid-December, while the A40 will arrive early next year.