AMD Radeon PRO W9070 vs NVIDIA RTX PRO 6000 Blackwell
GPU Specs Compare
Graphics Card
Release Date
Unknown
Mar 2025
Generation
Mining GPUs
Blackwell PRO W
Type
Desktop
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1120 MHz
1590 MHz
Boost Clock
1206 MHz
2617 MHz
Memory Clock
2100 MHz
1750 MHz
Memory
Memory Size
4GB
96GB
Memory Type
GDDR5
GDDR7
Memory Bus
256bit
512bit
Bandwidth
268.8GB/s
1.79TB/s
Render Config
Compute Units
32
-
Shading Units
2048
24064
TMUs
128
752
ROPs
32
192
Tensor Cores
128
752
RT Cores
64
188
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
2 MB
128 MB
L3 Cache
64 MB
-
SM Count
-
188
Theoretical Performance
Pixel Rate
38.59 GPixel/s
502.5 GPixel/s
Texture Rate
154.4 GTexel/s
1968.0 GTexel/s
FP16 (half)
4.940 TFLOPS
126.0 TFLOPS
FP32 (float)
4.940 TFLOPS
126.0 TFLOPS
FP64 (double)
308.7 GFLOPS
1.968 TFLOPS
Graphics Processor
GPU Name
Polaris 20
GB202
GPU Variant
Navi 48 XTW
-
Architecture
GCN 4.0
Blackwell 2.0
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
5 nm
Transistors
5.7 billion
92.2 billion
Die Size
232 mm²
750 mm²
Board Design
TDP
180W
600W
Suggested PSU
450 W
1000 W
Outputs
1x HDMI 2.0b
4x DisplayPort 2.1b
Power Connectors
2x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.4
Shader Model
6.7
6.9
CUDA
-
12.0
📊 Benchmark
3DMark Time Spy
-
42,269
3DMark Time Spy Extreme
-
27,891
3DMark Speed Way
-
15,642