Geekbench ML Score

330
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 06:45 AM
Views 1

System Information

System Information
Operating System iOS 15.1
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 209
22.4 IPS
 
Image Classification (F16)
100% 204
21.8 IPS
 
Image Classification (I8)
81% 339
36.4 IPS
 
Image Segmentation (F32)
100% 398
2.46 IPS
 
Image Segmentation (F16)
100% 397
2.45 IPS
 
Image Segmentation (I8)
89% 642
3.97 IPS
 
Pose Estimation (F32)
100% 127
0.52 IPS
 
Pose Estimation (F16)
100% 117
0.47 IPS
 
Pose Estimation (I8)
80% 122
0.50 IPS
 
Object Detection (F32)
100% 358
12.6 IPS
 
Object Detection (F16)
100% 360
12.7 IPS
 
Object Detection (I8)
52% 487
17.1 IPS
 
Face Detection (F32)
100% 428
4.91 IPS
 
Face Detection (F16)
100% 431
4.95 IPS
 
Face Detection (I8)
75% 479
5.51 IPS
 
Text Classification (F32)
100% 476
188.2 IPS
 
Text Classification (F16)
100% 482
190.8 IPS
 
Machine Translation (F32)
100% 462
71.2 IPS
 
Machine Translation (F16)
100% 470
72.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download