Taken from videocardz
The graphics card pictured below is the upcoming flagship model for the Quadro RTX series based on Ampere architecture. NVIDIA has not yet been confirmed to be developing an RTX A8000 variant with more memory.
The RTX (A)6000 allegedly features GA102 GPU with 10752 CUDA cores. Unlike the gaming GeForce RTX series, the Quadro would sport GDDR6 non-X memory. This is because GDDR6X memory is not a manufacturer in a capacity that the Quadro series requires. It may also be a reason why Quadro 6000 launches first, as GDDR6X memory with 2GB capacity per module is expected next year. The memory speed is 3 Gbps lower than RTX 3080’s (16 Gbps).
The card appears to also use two fans and a short PCB, however, it remains to be seen if the PCB is shaped similarly to the GeForce RTX board.
The Quadro RTX A6000 is expected to debut on October 5th, when NVIDIA will host its GTC Digital event.