NVIDIA B300 vs AMD Radeon Pro WX 8200

GPU · Specs Compare

Products
GPU NVIDIA B300 NVIDIA · 2025-09
GPU AMD Radeon Pro WX 8200 AMD · 2018-08
Graphics Card
Release Date
Sep 2025
Aug 2018
Generation
Server Blackwell
Radeon Pro
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1665 MHz
1200 MHz
Boost Clock
2032 MHz
1500 MHz
Memory Clock
2000 MHz
1000 MHz
Memory
Memory Size
144GB
8GB
Memory Type
HBM3e
HBM2
Memory Bus
4096bit
2048bit
Bandwidth
4.10TB/s
512.0GB/s
Render Config
SM Count
148
—
Shading Units
18944
3584
TMUs
592
224
ROPs
24
64
Tensor Cores
592
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
4 MB
Compute Units
—
56
Theoretical Performance
Pixel Rate
48.77 GPixel/s
96.00 GPixel/s
Texture Rate
1202.9 GTexel/s
336.0 GTexel/s
FP16 (half)
1231.8 TFLOPS
21.50 TFLOPS
FP32 (float)
76.99 TFLOPS
10.75 TFLOPS
FP64 (double)
1202.9 GFLOPS
672.0 GFLOPS
Graphics Processor
GPU Name
GB110
Vega 10
Architecture
Blackwell Ultra
GCN 5.0
Foundry
TSMC
GlobalFoundries
Process Size
5 nm
14 nm
Transistors
104 billion
12.5 billion
Die Size
Unknown
495 mm²
GPU Variant
—
Vega 10 XT(215-0894200)
Board Design
TDP
1400W
230W
Suggested PSU
1800 W
550 W
Outputs
No outputs
4x mini-DisplayPort 1.4a
Power Connectors
—
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
10.3
—
Shader Model
N/A
6.4
▲ Specs Compare Data sourced from official specifications and benchmark tests.