Geekbench ML Score

1006
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 02:17 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 829
88.9 IPS
 
Image Classification (F16)
100% 781
83.7 IPS
 
Image Classification (I8)
81% 464
49.7 IPS
 
Image Segmentation (F32)
100% 1193
7.37 IPS
 
Image Segmentation (F16)
100% 1147
7.08 IPS
 
Image Segmentation (I8)
89% 1504
9.29 IPS
 
Pose Estimation (F32)
100% 447
1.81 IPS
 
Pose Estimation (F16)
100% 437
1.77 IPS
 
Pose Estimation (I8)
80% 512
2.07 IPS
 
Object Detection (F32)
100% 1145
40.2 IPS
 
Object Detection (F16)
100% 1148
40.3 IPS
 
Object Detection (I8)
52% 762
26.7 IPS
 
Face Detection (F32)
100% 1458
16.7 IPS
 
Face Detection (F16)
100% 1421
16.3 IPS
 
Face Detection (I8)
75% 863
9.92 IPS
 
Text Classification (F32)
100% 1404
555.1 IPS
 
Text Classification (F16)
100% 1407
556.3 IPS
 
Machine Translation (F32)
100% 2267
349.4 IPS
 
Machine Translation (F16)
100% 2279
351.2 IPS
 

Compare

Set Baseline