iPad17,1 MACHENIKE L16P Difference
Single Precision 5796 15845 36.6%
iPad17,1
 
MACHENIKE L16P
 
Half Precision 37217 27643 134.6%
iPad17,1
 
MACHENIKE L16P
 
Quantized 51999 12392 419.6%
iPad17,1
 
MACHENIKE L16P
 
Geekbench AI 1.8.0 Geekbench AI 1.7.0

System Information

iPad17,1 MACHENIKE L16P
AI Framework Core ML ONNX
AI Backend Neural Engine DirectML
AI Device ARM NVIDIA GeForce RTX 4060 Laptop GPU
Operating System iOS 27.2.1 Microsoft Windows 11 (64-bit)
Model iPad17,1 MACHENIKE L16P
Processor ARM @ 4.43 GHz
1 Processor, 9 Cores
Intel Core i9-12900HX @ 2.30 GHz
1 Processor, 16 Cores, 24 Threads
Processor ID ARM GenuineIntel Family 6 Model 151 Stepping 2
Processor Codename
Processor Package
Motherboard J817AP MACHENIKE L16P
Northbridge
Southbridge
BIOS American Megatrends International, LLC. N.1.01HAI03
Memory 11.25 GB 32.00 GB

AI Performance

iPad17,1 MACHENIKE L16P Difference
Image Classification (SP) 2339 5359 43.6%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (HP) 14835 11008 134.8%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (Q) 20277 5067 400.2%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (SP) 2397 11397 21.0%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (HP) 23467 15987 146.8%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (Q) 32933 10377 317.4%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (SP) 11283 84795 13.3%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (HP) 172013 235842 72.9%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (Q) 324964 75254 431.8%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (SP) 2735 7133 38.3%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (HP) 16169 14101 114.7%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (Q) 22209 6212 357.5%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (SP) 4637 20065 23.1%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (HP) 44893 29632 151.5%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (Q) 66625 17014 391.6%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (SP) 8691 36787 23.6%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (HP) 102615 70858 144.8%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (Q) 173610 29563 587.3%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (SP) 27454 128122 21.4%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (HP) 286155 346171 82.7%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (Q) 372110 115794 321.4%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (SP) 6579 25187 26.1%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (HP) 54220 44790 121.1%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (Q) 83506 18731 445.8%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (SP) 6586 3416 192.8%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (HP) 5060 4041 125.2%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (Q) 5309 1889 281.0%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (SP) 5163 3320 155.5%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (HP) 14559 3384 430.2%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (Q) 15718 1687 931.7%
iPad17,1
 
MACHENIKE L16P