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