Geekbench ML Score

2495
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 02:49 AM
Views 1

System Information

System Information
Operating System iOS 16.1
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2870
307.5 IPS
 
Image Classification (F16)
100% 4549
487.4 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 6471
40.0 IPS
 
Image Segmentation (F16)
100% 8984
55.5 IPS
 
Image Segmentation (I8)
89% 1367
8.44 IPS
 
Pose Estimation (F32)
100% 2396
9.70 IPS
 
Pose Estimation (F16)
100% 5120
20.7 IPS
 
Pose Estimation (I8)
80% 258
1.05 IPS
 
Object Detection (F32)
100% 3346
117.4 IPS
 
Object Detection (F16)
100% 3368
118.2 IPS
 
Object Detection (I8)
52% 1067
37.4 IPS
 
Face Detection (F32)
100% 5880
67.5 IPS
 
Face Detection (F16)
97% 9980
114.7 IPS
 
Face Detection (I8)
75% 1048
12.0 IPS
 
Text Classification (F32)
100% 1905
753.5 IPS
 
Text Classification (F16)
100% 1994
788.5 IPS
 
Machine Translation (F32)
100% 2261
348.5 IPS
 
Machine Translation (F16)
100% 2254
347.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download