Geekbench ML Score

467
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 01:26 PM
Views 2

System Information

System Information
Operating System iOS 15.4
Model iPhone 6s Plus
Model IDiPhone8,2
Motherboard N66mAP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 499
53.5 IPS
 
Image Classification (F16)
100% 662
70.9 IPS
 
Image Classification (I8)
81% 155
16.6 IPS
 
Image Segmentation (F32)
100% 1166
7.20 IPS
 
Image Segmentation (F16)
100% 1906
11.8 IPS
 
Image Segmentation (I8)
89% 277
1.71 IPS
 
Pose Estimation (F32)
100% 445
1.80 IPS
 
Pose Estimation (F16)
100% 860
3.48 IPS
 
Pose Estimation (I8)
80% 49
0.20 IPS
 
Object Detection (F32)
100% 672
23.6 IPS
 
Object Detection (F16)
100% 810
28.4 IPS
 
Object Detection (I8)
52% 197
6.90 IPS
 
Face Detection (F32)
100% 1110
12.8 IPS
 
Face Detection (F16)
97% 1974
22.7 IPS
 
Face Detection (I8)
75% 192
2.20 IPS
 
Text Classification (F32)
100% 424
167.7 IPS
 
Text Classification (F16)
98% 460
182.0 IPS
 
Machine Translation (F32)
100% 313
48.2 IPS
 
Machine Translation (F16)
100% 330
50.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download