NVIDIA RTX A6000 vs NVIDIA GB10
GPU · Specs Compare
Graphics Card
Release Date
Oct 2020
Oct 2025
Generation
Quadro Ampere
Server Blackwell
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1410 MHz
1665 MHz
Boost Clock
1800 MHz
2418 MHz
Memory Clock
2000 MHz
1067 MHz
Memory
Memory Size
48GB
128GB
Memory Type
GDDR6
LPDDR5X
Memory Bus
384bit
256bit
Bandwidth
768.0GB/s
273.2GB/s
Render Config
SM Count
84
48
Shading Units
10752
6144
TMUs
336
384
ROPs
112
48
Tensor Cores
336
384
RT Cores
84
48
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
6 MB
50 MB
Theoretical Performance
Pixel Rate
201.6 GPixel/s
116.1 GPixel/s
Texture Rate
604.8 GTexel/s
928.5 GTexel/s
FP16 (half)
38.71 TFLOPS
29.71 TFLOPS
FP32 (float)
38.71 TFLOPS
29.71 TFLOPS
FP64 (double)
604.8 GFLOPS
464.3 GFLOPS
Graphics Processor
GPU Name
GA102
GB20B
Architecture
Ampere
Blackwell 2.0
Foundry
Samsung
TSMC
Process Size
8 nm
3 nm
Transistors
28.3 billion
Unknown
Die Size
628 mm²
Unknown
Board Design
TDP
300W
140W
Suggested PSU
700 W
300 W
Outputs
4x DisplayPort 1.4a
1x HDMI
Power Connectors
8-pin EPS
None
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.6
12.1
Shader Model
6.7
N/A
Benchmark
3DMark Time Spy
17,742
—
3DMark Time Spy Extreme
9,324
—
OctaneBench
600
—
3DMark Speed Way
4,965
—
Blender
5,387
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.