Geekbench ML Score

428
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:08 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 343
36.8 IPS
 
Image Classification (F16)
100% 408
43.8 IPS
 
Image Classification (I8)
81% 320
34.2 IPS
 
Image Segmentation (F32)
100% 541
3.34 IPS
 
Image Segmentation (F16)
100% 629
3.89 IPS
 
Image Segmentation (I8)
89% 588
3.63 IPS
 
Pose Estimation (F32)
100% 440
1.78 IPS
 
Pose Estimation (F16)
100% 440
1.78 IPS
 
Pose Estimation (I8)
80% 117
0.47 IPS
 
Object Detection (F32)
100% 708
24.8 IPS
 
Object Detection (F16)
100% 653
22.9 IPS
 
Object Detection (I8)
52% 400
14.0 IPS
 
Face Detection (F32)
100% 831
9.55 IPS
 
Face Detection (F16)
100% 773
8.89 IPS
 
Face Detection (I8)
75% 418
4.80 IPS
 
Text Classification (F32)
98% 162
63.9 IPS
 
Text Classification (F16)
98% 143
56.5 IPS
 
Machine Translation (F32)
100% 657
101.3 IPS
 
Machine Translation (F16)
100% 651
100.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download