AMD Radeon AI PRO R9700 vs NVIDIA B200 SXM6
GPU · Specs Compare
Graphics Card
Release Date
Jul 2025
Nov 2024
Generation
Radeon Pro Navi
Server Blackwell
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
1660 MHz
120 MHz
Boost Clock
2920 MHz
1830 MHz
Memory Clock
2518 MHz
2000 MHz
Memory
Memory Size
32GB
180GB
Memory Type
GDDR6
HBM3e
Memory Bus
256bit
8192bit
Bandwidth
644.6GB/s
8.19TB/s
Render Config
Compute Units
64
—
Shading Units
4096
18944
TMUs
256
592
ROPs
128
24
Tensor Cores
128
592
RT Cores
64
—
L2 Cache
8 MB
126 MB
L3 Cache
64 MB
—
SM Count
—
148
L1 Cache
—
256 KB (per SM)
Theoretical Performance
Pixel Rate
373.8 GPixel/s
43.92 GPixel/s
Texture Rate
747.5 GTexel/s
1083.4 GTexel/s
FP16 (half)
95.68 TFLOPS
1109.4 TFLOPS
FP32 (float)
47.84 TFLOPS
69.34 TFLOPS
FP64 (double)
1495.0 GFLOPS
34.67 TFLOPS
Graphics Processor
GPU Name
Navi 48
GB100
GPU Variant
Navi 48 XTW
GB100-886N-A1
Architecture
RDNA 4.0
Blackwell
Foundry
TSMC
TSMC
Process Size
4 nm
5 nm
Transistors
53.9 billion
208 billion
Die Size
357 mm²
1628 mm²
Board Design
TDP
300W
1000W
Suggested PSU
700 W
1400 W
Outputs
1x HDMI 2.1b3x DisplayPort 2.1a
No outputs
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
2.2
3.0
Vulkan
1.4
N/A
Shader Model
6.8
N/A
CUDA
—
10.0
▲ Specs Compare
Data sourced from official specifications and benchmark tests.