The NVIDIA RTX A6000 has been the only workstation Ampere graphics card you can get, but that is about to change soon as the company prepares the RTX A5000 and RTX A4000 as the less expensive pro options for content creators and heavy users.
NVIDIA RTX A5000 and RTX A4000 Workstation Ampere graphics cards detected, portable variants also coming
NVIDIA RTX A5000 and RTX A4000 graphics cards are based on the Ampere GPU architecture and are siblings of the flagship RTX A6000. Both graphics cards were submitted for OpenCL 1.2 validation to Khronos Group. Currently NVIDIA RTX A6000 uses the full GA102 GPU, so it can be assumed that RTX A5000 and RTX A4000 will also come with full configuration of NVIDIA’s Ampere GA104 and GA106 GPUs.
That will give the NVIDIA RTX A5000 a total of 6144 CUDA cores, and considering that we’ll be looking at a 256-bit bus, we can expect either 16 or 32 GB of GDDR6 memory. The NVIDIA RTX A4000 would get the full GA106 GPU with 3840 CUDA cores and could end up with up to 12 GB of GDDR6 memory running across a 192-bit bus interface.
NVIDIA Ampere Workstation Graphics Card:
|Graphics card||NVIDIA RTX A4000||NVIDIA RTX A5000||NVIDIA RTX A6000|
|GPU||Ampere GA106 GPU?||Ampere GA104 GPU?||Ampere GA102 GPU|
|GPU process||Samsung 8nm||Samsung 8nm||Samsung 8nm|
|The Size||276 mm²||392 mm²||628mm²|
|Boost Clock||TBC||TBC||1860 MHz|
|Simple precision||TBC||TBC||40 TFLOPs|
|VRAM||12 GB GDDR6||16-32 GB GDDR6||48 GB GDDR6|
|NVLINK VRAM||TBC||TBC||96 GB GDDR6|
|Memory bandwidth||TBC||TBC||768 GB / s|
|Starting price||TBC||TBC||$ 4650 US|
|Release date||TBC||TBC||December 2020|
In addition to the submission, the NVIDIA RTX A5000 workstation graphics card has been discovered in a workstation laptop consisting of an Intel Core i7-11600H CPU. The laptop was tested in the reference for Ashes of The Singularity, and although we do not get any new details regarding the GPU itself, the CPU is tested here surprisingly, since it is the first time we see since the 8th generation that a Core i7 SKU gets 6 cores and 12 threads. Of course, this is a Tiger Lake-H laptop CPU, but it looks like it will have a base clock of 2.90 GHz and 9 MB L3 cache.
No other details for the laptop have been confirmed and the score should be rejected as it is slower than RTX 3060 due to non-optimized drivers. All we can say is that NVIDIA is in fact preparing cheaper workstation graphics cards based on the Ampere GPU architecture, and we can expect them to be launched in the coming months in both desktop and portable discrete flavors.
News sources: Komachi, Leakbench