B200 SXM 192 GB vs Radeon Pro WX 3200
We compared two Desktop platform GPUs: 96GB VRAM B200 SXM 192 GB and 4GB VRAM Radeon Pro WX 3200 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
B200 SXM 192 GB Advantages
Released 4 years and 6 months late
Boost Clock1837MHz
More VRAM (96GB vs 4GB)
Larger VRAM bandwidth (4.10TB/s vs 96.00GB/s)
16256 additional rendering cores
Radeon Pro WX 3200 Advantages
Lower TDP (65W vs 1000W)
Score
Benchmark
FP32 (float)
B200 SXM 192 GB
+3644%
62080
Radeon Pro WX 3200
1658
Graphics Card
Jan 2024
Release Date
Jul 2019
Server Blackwell
Generation
Radeon Pro
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
1665 MHz
Base Clock
-
1837 MHz
Boost Clock
-
2000 MHz
Memory Clock
1500 MHz
Memory
96GB
Memory Size
4GB
HBM3e
Memory Type
GDDR5
4096bit
Memory Bus
128bit
4.10TB/s
Bandwidth
96.00GB/s
Render Config
-
Compute Units
10
132
SM Count
-
16896
Shading Units
640
528
TMUs
32
24
ROPs
16
528
Tensor Cores
-
256 KB (per SM)
L1 Cache
16 KB (per CU)
50 MB
L2 Cache
512 KB
Theoretical Performance
44.09 GPixel/s
Pixel Rate
20.72 GPixel/s
969.9 GTexel/s
Texture Rate
41.44 GTexel/s
248.3 TFLOPS
FP16 (half)
1.658 TFLOPS
62.08 TFLOPS
FP32 (float)
1.658 TFLOPS
31.04 TFLOPS
FP64 (double)
103.6 GFLOPS
Board Design
1000W
TDP
65W
1400 W
Suggested PSU
250 W
No outputs
Outputs
4x mini-DisplayPort 1.4a
-
Power Connectors
None
Graphics Processor
GB100
GPU Name
Polaris 23
-
GPU Variant
Polaris 23 XT GL
Blackwell
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
5 nm
Process Size
14 nm
104 billion
Transistors
2.2 billion
Unknown
Die Size
103 mm²
Graphics Features
N/A
DirectX
12 (12_0)
N/A
OpenGL
4.6
3.0
OpenCL
2.1
N/A
Vulkan
1.2
10.0
CUDA
-
N/A
Shader Model
6.4
