Geekbench ML Score

4658
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 27 2024 07:20 AM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,5
Model IDiPad16,5
Motherboard J720AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 4.41 GHz
Cluster 13 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.20 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1902
356.0 IPS
 
Image Classification (F16)
100% 2530
473.5 IPS
 
Image Classification (I8)
99% 2522
472.0 IPS
 
Image Segmentation (F32)
100% 1178
19.7 IPS
 
Image Segmentation (F16)
100% 1141
19.1 IPS
 
Image Segmentation (I8)
100% 1136
19.0 IPS
 
Pose Estimation (F32)
100% 9486
11.5 IPS
 
Pose Estimation (F16)
100% 17871
21.6 IPS
 
Pose Estimation (I8)
100% 17880
21.7 IPS
 
Object Detection (F32)
100% 1884
140.7 IPS
 
Object Detection (F16)
100% 2577
192.4 IPS
 
Object Detection (I8)
97% 1884
140.7 IPS
 
Face Detection (F32)
100% 3508
41.7 IPS
 
Face Detection (F16)
97% 5538
65.8 IPS
 
Face Detection (I8)
97% 5504
65.4 IPS
 
Depth Estimation (F32)
100% 7490
58.1 IPS
 
Depth Estimation (F16)
100% 10937
84.8 IPS
 
Depth Estimation (I8)
99% 10985
85.2 IPS
 
Style Transfer (F32)
100% 23286
30.6 IPS
 
Style Transfer (F16)
100% 34147
44.9 IPS
 
Style Transfer (I8)
100% 34062
44.8 IPS
 
Image Super-Resolution (F32)
100% 5880
210.0 IPS
 
Image Super-Resolution (F16)
100% 6965
248.7 IPS
 
Image Super-Resolution (I8)
100% 6949
248.2 IPS
 
Text Classification (F32)
100% 2826
4.06 KIPS
 
Text Classification (F16)
100% 4645
6.68 KIPS
 
Text Classification (I8)
96% 4648
6.68 KIPS
 
Machine Translation (F32)
100% 1609
29.6 IPS
 
Machine Translation (F16)
100% 1850
34.0 IPS
 
Machine Translation (I8)
99% 1607
29.6 IPS
 

Compare

Set Baseline Geekbench 6 now available