iPad17,1 MACHENIKE L16P Difference
Single Precision 5852 15951 36.7%
iPad17,1
 
MACHENIKE L16P
 
Half Precision 37285 28615 130.3%
iPad17,1
 
MACHENIKE L16P
 
Quantized 51588 12627 408.6%
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) 2341 5499 42.6%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (HP) 14863 11829 125.6%
iPad17,1
 
MACHENIKE L16P
 
Image Classification (Q) 20221 5219 387.4%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (SP) 2428 11584 21.0%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (HP) 23426 16527 141.7%
iPad17,1
 
MACHENIKE L16P
 
Image Segmentation (Q) 32852 10340 317.7%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (SP) 11251 86509 13.0%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (HP) 176150 222608 79.1%
iPad17,1
 
MACHENIKE L16P
 
Pose Estimation (Q) 326168 75336 433.0%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (SP) 2767 7383 37.5%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (HP) 17135 15750 108.8%
iPad17,1
 
MACHENIKE L16P
 
Object Detection (Q) 23246 6421 362.0%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (SP) 5261 19248 27.3%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (HP) 46839 32849 142.6%
iPad17,1
 
MACHENIKE L16P
 
Face Detection (Q) 70765 17192 411.6%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (SP) 8658 35945 24.1%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (HP) 103284 71111 145.2%
iPad17,1
 
MACHENIKE L16P
 
Depth Estimation (Q) 175364 30228 580.1%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (SP) 27668 133065 20.8%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (HP) 294423 347913 84.6%
iPad17,1
 
MACHENIKE L16P
 
Style Transfer (Q) 372974 119147 313.0%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (SP) 6550 25248 25.9%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (HP) 53503 45108 118.6%
iPad17,1
 
MACHENIKE L16P
 
Image Super-Resolution (Q) 84099 20172 416.9%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (SP) 6208 3372 184.1%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (HP) 4443 4027 110.3%
iPad17,1
 
MACHENIKE L16P
 
Text Classification (Q) 4524 1853 244.1%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (SP) 5203 3344 155.6%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (HP) 14592 3638 401.1%
iPad17,1
 
MACHENIKE L16P
 
Machine Translation (Q) 15054 1706 882.4%
iPad17,1
 
MACHENIKE L16P