NVIDIA L20 vs NVIDIA P106M
GPU · Specs Compare
Graphics Card
Release Date
Nov 2023
Jan 2019
Generation
Server Ada
Mining GPUs
Type
Desktop
Mobile
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1440 MHz
1291 MHz
Boost Clock
2520 MHz
1291 MHz
Memory Clock
2250 MHz
1502 MHz
Memory
Memory Size
48GB
4GB
Memory Type
GDDR6
GDDR5
Memory Bus
384bit
128bit
Bandwidth
864.0GB/s
96.13GB/s
Render Config
SM Count
92
9
Shading Units
11776
1152
TMUs
368
72
ROPs
128
32
Tensor Cores
368
—
RT Cores
92
—
L1 Cache
128 KB (per SM)
48 KB (per SM)
L2 Cache
96 MB
1280 KB
Theoretical Performance
Pixel Rate
322.6 GPixel/s
41.31 GPixel/s
Texture Rate
927.4 GTexel/s
92.95 GTexel/s
FP16 (half)
59.35 TFLOPS
46.48 GFLOPS
FP32 (float)
59.35 TFLOPS
2.974 TFLOPS
FP64 (double)
927.4 GFLOPS
92.95 GFLOPS
Graphics Processor
GPU Name
AD102
GP106
GPU Variant
AD102
GP106-505-KC-A1
Architecture
Ada Lovelace
Pascal
Foundry
TSMC
TSMC
Process Size
5 nm
16 nm
Transistors
76.3 billion
4.4 billion
Die Size
609 mm²
200 mm²
Board Design
TDP
275W
75W
Suggested PSU
600 W
—
Outputs
4x DisplayPort 1.4a
Portable Device Dependent
Power Connectors
1x 16-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
1.3
CUDA
8.9
6.1
Shader Model
6.9
6.8
▲ Specs Compare
Data sourced from official specifications and benchmark tests.