NVIDIA RTX PRO 6000D Blackwell Max-Q vs NVIDIA Rubin Ultra GPU
GPU · Specs Compare
Graphics Card
Release Date
Mar 2025
Jan 2027
Generation
Blackwell PRO W
Server Rubin
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
1590 MHz
700 MHz
Boost Clock
2288 MHz
2267 MHz
Memory Clock
1750 MHz
1900 MHz
Memory
Memory Size
96GB
1024GB
Memory Type
GDDR7
HBM4e
Memory Bus
512bit
32768bit
Bandwidth
1.79TB/s
31.1TB/s
Render Config
SM Count
188
448
Shading Units
24064
57344
TMUs
752
1792
ROPs
192
24
Tensor Cores
752
1792
RT Cores
188
—
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
128 MB
128 MB
Theoretical Performance
Pixel Rate
439.3 GPixel/s
54.41 GPixel/s
Texture Rate
1720.6 GTexel/s
4062.5 GTexel/s
FP16 (half)
110.1 TFLOPS
520.0 TFLOPS
FP32 (float)
110.1 TFLOPS
260.0 TFLOPS
FP64 (double)
1.721 TFLOPS
65.00 TFLOPS
Graphics Processor
GPU Name
GB202
GR110
Architecture
Blackwell 2.0
Rubin Ultra
Foundry
TSMC
TSMC
Process Size
5 nm
3 nm
Transistors
92.2 billion
670 billion
Die Size
750 mm²
2912 mm²
Board Design
TDP
300W
3600W
Suggested PSU
700 W
4000 W
Outputs
4x DisplayPort 2.1b
No outputs
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.4
N/A
CUDA
12.0
10.7
Shader Model
6.8
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.