AMD Radeon Pro WX 4100 vs NVIDIA L20
GPU · Specs Compare
Graphics Card
Release Date
Nov 2016
Nov 2023
Generation
Radeon Pro
Server Ada
Type
Desktop
Desktop
Bus Interface
PCIe 3.0 x8
PCIe 4.0 x16
Clock Speeds
Base Clock
1125 MHz
1440 MHz
Boost Clock
1201 MHz
2520 MHz
Memory Clock
1500 MHz
2250 MHz
Memory
Memory Size
4GB
48GB
Memory Type
GDDR5
GDDR6
Memory Bus
128bit
384bit
Bandwidth
96.00GB/s
864.0GB/s
Render Config
Compute Units
16
—
Shading Units
1024
11776
TMUs
64
368
ROPs
16
128
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
96 MB
SM Count
—
92
Tensor Cores
—
368
RT Cores
—
92
Theoretical Performance
Pixel Rate
19.22 GPixel/s
322.6 GPixel/s
Texture Rate
76.86 GTexel/s
927.4 GTexel/s
FP16 (half)
2.460 TFLOPS
59.35 TFLOPS
FP32 (float)
2.460 TFLOPS
59.35 TFLOPS
FP64 (double)
153.7 GFLOPS
927.4 GFLOPS
Graphics Processor
GPU Name
Baffin
AD102
GPU Variant
Baffin XT
AD102
Architecture
GCN 4.0
Ada Lovelace
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
5 nm
Transistors
3 billion
76.3 billion
Die Size
123 mm²
609 mm²
Board Design
TDP
50W
275W
Suggested PSU
250 W
600 W
Outputs
4x mini-DisplayPort 1.4a
4x DisplayPort 1.4a
Power Connectors
None
1x 16-pin
Graphics Features
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.2
1.4
Shader Model
6.4
6.9
CUDA
—
8.9
Benchmark
3DMark Time Spy
1,520
—
3DMark Time Spy Extreme
774
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.