NVIDIA recently unveiled its consumer-targeted AmFire cards of the GeForce RTX 30 series and soon, the company will also unveil its ProCumer and Workstation Quad RTX graphics cards to the Ampere lineup.
NVIDIA Quadro RTX (Ampere) Graphics Card with Full Fat GA102 GPU and 48 GB GDDR6 Memory Spot
The NVIDIA Quadro RTX lineup was first introduced with the Turing GPU and will soon be upgraded to the new Ampere graphics architecture. In a tweet by Moore’s law is dead (Via Videocardz), he says the picture is for the next-generation Quadro RTX graphics card with a full-fat GA 102 GPU.
The leaked image we are seeing is from the NVIDIA control panel which lists several key specifications of the card. It has not been told what the card will be called, but according to Kopite7kimi, the card could probably go as the Quadro RTX A6000, which means that there will be room for a higher end Quadro RTX A8000 in the future.
More big Ampere cards are coming, and I have pics … pic.twitter.com/XxQK29eQ9i
– Moore’s law is dead (@mooreslawisdead) September 12, 2020
– kopite7kimi (@ kopite7kimi) September 13, 2020
The list of specifications is 10752 CUDA cores arranged in 84 SM. This is the full-fat Ampere GA102 GPU we want to be faster than the GeForce RTX 3090 as it packs 2% more cores, though it mostly depends on the clock speed at which the card runs. The Quadro RTX A6000 operates at 1860 MHz boost clock, which should be equal to 40 TFLOPs of compute horsepower.
In terms of memory, the card can carry a total of 48 GB of GDDR6 memory in a 384-bit wide bus interface. This should equal the total bandwidth of 768 GB / s. Now the bandwidth is lower than the NVIDIA GeForce RTX 3090 which should be around 936 GB / s since the GDDR6X memory dies. This is certainly an interesting option and may mean that we may see the GDDR6X implementation next year with a higher end Quadro SKU as high-density GDDR6X chips are going into mass production in early 2021 . There is also a new thing. The Titan variant is coming soon but we have no specification.
NVIDIA Quadro RTX Series Graphics Card Lineup:
|graphics card||Quadro GV100||Quadro RTX 5000||Quadro RTX 6000||Quadro RTX 8000||Quadro RTX (Ampere)|
|GPU||Volta GPU||Turing GPU||Turing GPU||Turing GPU||Ampere gpu|
|GPU Cores||5120 crores||3072 crore||4608 crores||4608 crores||10752 Crore|
|Tensor course||640 million||384 crores||576 crores is||576 crores is||656 crores is|
|Boost clock||1.62 GHz||1.81 GHz||1.77 GHz||1.77 GHz||1.Hz 6 GHz|
|Single precision||16.66 TFLOPs||11.2 TFLOPs||16.31 TFLOPs||16.31 TFLOPs||30 TFLOPs|
|Ray tracing imagery||N / A||6 GigaRays / Sec||10 GigaRays / Sec||10 GigaRays / Sec||TBA|
|VRAM||32 GB HBM 2||16 GB GDDR6||24 GB GDDR 6||48 GB GDDR 6||48 GB GDDR 6|
|NVLINK VRAM||N / A||32 GB with NVLINK||48 GB with NVLINK||96 GB with NVLINK||96 GB with NVLINK|
|Memory Bandwidth||870 GB / s||448 GB / s||672 GB / s||672 GB / s||768 GB / s|
|TDP||250W||~ 160W||~ 200W||~ 225W||TBA|
|cost||$ 9000 U.S.||$ 2300 U.S.||$ 6300 US||$ 10000 U.S.||TBA|
|commencement date||2018||Q4 2018||Q4 2018||Q4 2018||Q4 2020?|
We also don’t know if NVIDIA will use its GA102 or GA100 GPU for use in its flagship Quadro and Titan graphics cards based on the Ampere architecture. If we hear more about the Quadro RTX Ampere line of graphics cards then we will keep you posted, but expect news in the coming month.