NVIDIA RTX A2000 Max-Q 8 GB vs NVIDIA Rubin Ultra GPU
GPU · Specs Compare
Graphics Card
Release Date
Apr 2021
Jan 2027
Generation
Ampere-MW
Server Rubin
Type
Mobile
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
607 MHz
700 MHz
Boost Clock
1177 MHz
2267 MHz
Memory Clock
1375 MHz
1900 MHz
Memory
Memory Size
8GB
1024GB
Memory Type
GDDR6
HBM4e
Memory Bus
128bit
32768bit
Bandwidth
176.0GB/s
31.1TB/s
Render Config
SM Count
20
448
Shading Units
2560
57344
TMUs
80
1792
ROPs
48
24
Tensor Cores
80
1792
RT Cores
20
—
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
2 MB
128 MB
Theoretical Performance
Pixel Rate
56.50 GPixel/s
54.41 GPixel/s
Texture Rate
94.16 GTexel/s
4062.5 GTexel/s
FP16 (half)
6.026 TFLOPS
520.0 TFLOPS
FP32 (float)
6.026 TFLOPS
260.0 TFLOPS
FP64 (double)
94.16 GFLOPS
65.00 TFLOPS
Graphics Processor
GPU Name
GA107
GR110
Architecture
Ampere
Rubin Ultra
Foundry
Samsung
TSMC
Process Size
8 nm
3 nm
Transistors
8.7 billion
670 billion
Die Size
200 mm²
2912 mm²
Board Design
TDP
95W
3600W
Outputs
Portable Device Dependent
No outputs
Power Connectors
None
—
Suggested PSU
—
4000 W
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
10.7
Shader Model
6.8
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.