Geekbench ML Score

2525
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:44 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 3.45 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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2923
313.2 IPS
 
Image Classification (F16)
100% 4555
488.0 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 6505
40.2 IPS
 
Image Segmentation (F16)
100% 9381
57.9 IPS
 
Image Segmentation (I8)
89% 1365
8.43 IPS
 
Pose Estimation (F32)
100% 2432
9.84 IPS
 
Pose Estimation (F16)
100% 5147
20.8 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 3333
117.0 IPS
 
Object Detection (F16)
100% 3634
127.5 IPS
 
Object Detection (I8)
52% 1068
37.5 IPS
 
Face Detection (F32)
100% 5954
68.4 IPS
 
Face Detection (F16)
97% 10070
115.7 IPS
 
Face Detection (I8)
75% 1046
12.0 IPS
 
Text Classification (F32)
100% 1874
741.4 IPS
 
Text Classification (F16)
100% 2068
817.8 IPS
 
Machine Translation (F32)
100% 2283
351.9 IPS
 
Machine Translation (F16)
100% 2291
353.1 IPS
 

Compare

Set Baseline