Geekbench ML Score

1013
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:03 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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% 825
88.4 IPS
 
Image Classification (F16)
100% 825
88.3 IPS
 
Image Classification (I8)
81% 476
51.0 IPS
 
Image Segmentation (F32)
100% 1276
7.88 IPS
 
Image Segmentation (F16)
100% 1280
7.91 IPS
 
Image Segmentation (I8)
89% 1485
9.17 IPS
 
Pose Estimation (F32)
100% 495
2.00 IPS
 
Pose Estimation (F16)
100% 487
1.97 IPS
 
Pose Estimation (I8)
80% 548
2.22 IPS
 
Object Detection (F32)
100% 1225
43.0 IPS
 
Object Detection (F16)
100% 1227
43.1 IPS
 
Object Detection (I8)
52% 758
26.6 IPS
 
Face Detection (F32)
100% 1563
18.0 IPS
 
Face Detection (F16)
100% 1538
17.7 IPS
 
Face Detection (I8)
75% 858
9.86 IPS
 
Text Classification (F32)
100% 981
388.1 IPS
 
Text Classification (F16)
100% 1037
410.0 IPS
 
Machine Translation (F32)
100% 2271
350.0 IPS
 
Machine Translation (F16)
100% 2272
350.1 IPS
 

Compare

Set Baseline