NVIDIA B100 vs AMD Radeon Pro 5600M
GPU · Specs Compare
Graphics Card
Release Date
Unknown
Jun 2020
Generation
Server Blackwell
Radeon Pro Mac
Type
Desktop
Mobile
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
700 MHz
1000 MHz
Boost Clock
975 MHz
1035 MHz
Memory Clock
2000 MHz
770 MHz
Memory
Memory Size
96GB
8GB
Memory Type
HBM3e
HBM2
Memory Bus
4096bit
2048bit
Bandwidth
4.10TB/s
394.2GB/s
Render Config
SM Count
132
—
Shading Units
16896
2560
TMUs
528
160
ROPs
24
64
Tensor Cores
528
—
L1 Cache
256 KB (per SM)
—
L2 Cache
50 MB
4 MB
Compute Units
—
40
Theoretical Performance
Pixel Rate
23.40 GPixel/s
66.24 GPixel/s
Texture Rate
514.8 GTexel/s
165.6 GTexel/s
FP16 (half)
131.8 TFLOPS
10.60 TFLOPS
FP32 (float)
32.95 TFLOPS
5.299 TFLOPS
FP64 (double)
16.47 TFLOPS
331.2 GFLOPS
Graphics Processor
GPU Name
GB102
Navi 12
Architecture
Blackwell
RDNA 1.0
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
104 billion
Unknown
Die Size
Unknown
Unknown
GPU Variant
—
Navi 12
Board Design
TDP
1000W
50W
Suggested PSU
1400 W
—
Outputs
No outputs
No outputs
Power Connectors
—
None
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.2
Vulkan
N/A
1.3
CUDA
10.1
—
Shader Model
N/A
6.5
Benchmark
3DMark Time Spy
—
3,973
3DMark Time Spy Extreme
—
2,546
▲ Specs Compare
Data sourced from official specifications and benchmark tests.