NVIDIA CMP 50HX vs NVIDIA RTX PRO 6000 Blackwell
GPU Specs Compare
Graphics Card
Release Date
Jun 2021
Mar 2025
Generation
Mining GPUs
Blackwell PRO W
Type
Desktop
Desktop
Bus Interface
PCIe 1.0 x4
PCIe 5.0 x16
Clock Speeds
Base Clock
1350 MHz
1590 MHz
Boost Clock
1545 MHz
2617 MHz
Memory Clock
1750 MHz
1750 MHz
Memory
Memory Size
10GB
96GB
Memory Type
GDDR6
GDDR7
Memory Bus
320bit
512bit
Bandwidth
560.0GB/s
1.79TB/s
Render Config
SM Count
56
188
Shading Units
3584
24064
TMUs
192
752
ROPs
80
192
Tensor Cores
448
752
RT Cores
56
188
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
5 MB
128 MB
Theoretical Performance
Pixel Rate
123.6 GPixel/s
502.5 GPixel/s
Texture Rate
296.6 GTexel/s
1968.0 GTexel/s
FP16 (half)
22.15 TFLOPS
126.0 TFLOPS
FP32 (float)
11.07 TFLOPS
126.0 TFLOPS
FP64 (double)
346.1 GFLOPS
1.968 TFLOPS
Graphics Processor
GPU Name
TU102
GB202
GPU Variant
TU102-100-A1
-
Architecture
Turing
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
12 nm
5 nm
Transistors
18.6 billion
92.2 billion
Die Size
754 mm²
750 mm²
Board Design
TDP
250W
600W
Suggested PSU
600 W
1000 W
Outputs
No outputs
4x DisplayPort 2.1b
Power Connectors
2x 8-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.4
CUDA
7.5
12.0
Shader Model
6.8
6.9
📊 Benchmark
3DMark Time Spy
-
42,269
3DMark Time Spy Extreme
-
27,891
3DMark Speed Way
-
15,642