Geekbench ML Score

2484
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 09 2022 04:51 PM
Views 16

System Information

System Information
Operating System iOS 16.0
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2864
306.8 IPS
 
Image Classification (F16)
100% 4542
486.7 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 6366
39.3 IPS
 
Image Segmentation (F16)
100% 9319
57.6 IPS
 
Image Segmentation (I8)
89% 1346
8.31 IPS
 
Pose Estimation (F32)
100% 2380
9.63 IPS
 
Pose Estimation (F16)
100% 5111
20.7 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 3285
115.3 IPS
 
Object Detection (F16)
100% 3607
126.6 IPS
 
Object Detection (I8)
52% 1060
37.2 IPS
 
Face Detection (F32)
100% 5904
67.8 IPS
 
Face Detection (F16)
97% 9983
114.7 IPS
 
Face Detection (I8)
75% 1030
11.8 IPS
 
Text Classification (F32)
100% 1919
758.9 IPS
 
Text Classification (F16)
100% 1842
728.7 IPS
 
Machine Translation (F32)
100% 2217
341.7 IPS
 
Machine Translation (F16)
100% 2220
342.1 IPS
 

Compare

Set Baseline