Geekbench ML Score

332
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 05:51 AM
Views 1

System Information

System Information
Operating System iOS 15.7
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% 210
22.6 IPS
 
Image Classification (F16)
100% 204
21.9 IPS
 
Image Classification (I8)
81% 339
36.3 IPS
 
Image Segmentation (F32)
100% 397
2.45 IPS
 
Image Segmentation (F16)
100% 398
2.46 IPS
 
Image Segmentation (I8)
89% 649
4.01 IPS
 
Pose Estimation (F32)
100% 128
0.52 IPS
 
Pose Estimation (F16)
100% 128
0.52 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 356
12.5 IPS
 
Object Detection (F16)
100% 359
12.6 IPS
 
Object Detection (I8)
52% 487
17.1 IPS
 
Face Detection (F32)
100% 432
4.96 IPS
 
Face Detection (F16)
100% 435
4.99 IPS
 
Face Detection (I8)
75% 483
5.55 IPS
 
Text Classification (F32)
100% 491
194.2 IPS
 
Text Classification (F16)
100% 508
200.8 IPS
 
Machine Translation (F32)
100% 429
66.1 IPS
 
Machine Translation (F16)
100% 444
68.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download