Geekbench ML Score

2105
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 09:37 AM
Views 1

System Information

System Information
Operating System iOS 16.3
Model iPhone14,7
Model IDiPhone14,7
Motherboard D27AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2335
250.2 IPS
 
Image Classification (F16)
100% 2259
242.1 IPS
 
Image Classification (I8)
81% 693
74.2 IPS
 
Image Segmentation (F32)
100% 5876
36.3 IPS
 
Image Segmentation (F16)
100% 8483
52.4 IPS
 
Image Segmentation (I8)
89% 1225
7.57 IPS
 
Pose Estimation (F32)
100% 1942
7.86 IPS
 
Pose Estimation (F16)
100% 4997
20.2 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 1882
66.0 IPS
 
Object Detection (F16)
100% 3561
125.0 IPS
 
Object Detection (I8)
52% 978
34.3 IPS
 
Face Detection (F32)
100% 5378
61.8 IPS
 
Face Detection (F16)
97% 9026
103.7 IPS
 
Face Detection (I8)
75% 915
10.5 IPS
 
Text Classification (F32)
100% 1052
416.2 IPS
 
Text Classification (F16)
100% 2132
843.3 IPS
 
Machine Translation (F32)
100% 2050
315.9 IPS
 
Machine Translation (F16)
100% 2052
316.2 IPS
 

Compare

Set Baseline