iPad17,1 MACHENIKE L16P Difference
Single Precision 5796 15951 36.3%
iPad17,1
 
MACHENIKE L16P
 
Half Precision 37217 28615 130.1%
iPad17,1
 
MACHENIKE L16P
 
Quantized 51999 12627 411.8%
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 5499 42.5%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (HP) 14835 11829 125.4%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (Q) 20277 5219 388.5%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (SP) 2397 11584 20.7%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (HP) 23467 16527 142.0%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (Q) 32933 10340 318.5%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (SP) 11283 86509 13.0%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (HP) 172013 222608 77.3%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (Q) 324964 75336 431.4%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (SP) 2735 7383 37.0%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (HP) 16169 15750 102.7%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (Q) 22209 6421 345.9%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (SP) 4637 19248 24.1%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (HP) 44893 32849 136.7%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (Q) 66625 17192 387.5%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (SP) 8691 35945 24.2%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (HP) 102615 71111 144.3%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (Q) 173610 30228 574.3%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (SP) 27454 133065 20.6%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (HP) 286155 347913 82.2%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (Q) 372110 119147 312.3%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (SP) 6579 25248 26.1%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (HP) 54220 45108 120.2%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (Q) 83506 20172 414.0%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (SP) 6586 3372 195.3%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (HP) 5060 4027 125.7%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (Q) 5309 1853 286.5%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (SP) 5163 3344 154.4%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (HP) 14559 3638 400.2%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (Q) 15718 1706 921.3%
iPad17,1
 
MACHENIKE L16P