NVIDIA GeForce RTX 3090 SUPER vs NVIDIA RTX A6000

What is the difference between NVIDIA GeForce RTX 3090 SUPER and NVIDIA RTX A6000. Find out which graphics card has better performance.

Graphics Processor (GPU)

GA102GPU NameGA102
AmpereArchitectureAmpere
SamsungFoundrySamsung
8 nmProcess Size8 nm
28,300 millionTransistors28,300 million
628 mm²Die Size628 mm²

Graphics Card

UnknownRelease DateOct 5th, 2020
GeForce 30FamilyQuadro
(Ax000)
ActiveProductionActive
1,699 USDLaunch Price4,649 USD
2021AvailabilityDec 15th, 2020
PCIe 4.0 x16Bus InterfacePCIe 4.0 x16

Memory

24 GBMemory Size48 GB
GDDR6XMemory TypeGDDR6
384 bitMemory Bus384 bit
1,018 GB/sBandwidth768.0 GB/s

Performance

189.8 GPixel/sPixel fillrate208.3 GPixel/s
569.5 GTexel/sTexture fillrate625.0 GTexel/s
36.45 TFLOPS (1:1)FP16 (half) performance40.00 TFLOPS (1:1)
36.45 TFLOPSFP32 (float) performance40.00 TFLOPS
569.5 GFLOPS (1:64)FP64 (double) performance1,250 GFLOPS (1:32)

Clock Speeds

1395 MHzBase Clock1455 MHz
1695 MHzBoost Clock1860 MHz
1325 MHz
21.2 Gbps effective
Memory Clock2000 MHz
16 Gbps effective

Render Config

10752Shading Units10752
336TMUs336
112ROPs112
84RT Cores84
128 KB (per SM)L1 Cache128 KB (per SM)
6 MBL2 Cache6 MB
84SM Count84
336Tensor Cores336

Board Design

Triple-slotSlot WidthDual-slot
336 mm
13.2 inches
Length267 mm
10.5 inches
140 mm
5.5 inches
Width112 mm
4.4 inches
400 WThermal design power (TDP)300 W
800 WSuggested PSU700 W
1x HDMI
3x DisplayPort
Display Connectors4x DisplayPort
1x 12-pinPower Connectors8-pin EPS

API support

12 Ultimate (12_2)DirectX12 Ultimate (12_2)
4.6OpenGL4.6
3.0OpenCL3.0
1.2Vulkan1.2
6.6Shader Model6.6
8.6CUDA8.6