Geekbench ML Score

626
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 08:13 AM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.59 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 396
42.4 IPS
 
Image Classification (F16)
100% 382
40.9 IPS
 
Image Classification (I8)
81% 771
82.6 IPS
 
Image Segmentation (F32)
100% 504
3.11 IPS
 
Image Segmentation (F16)
100% 500
3.09 IPS
 
Image Segmentation (I8)
89% 1226
7.57 IPS
 
Pose Estimation (F32)
100% 243
0.98 IPS
 
Pose Estimation (F16)
100% 299
1.21 IPS
 
Pose Estimation (I8)
80% 358
1.45 IPS
 
Object Detection (F32)
100% 625
21.9 IPS
 
Object Detection (F16)
100% 620
21.8 IPS
 
Object Detection (I8)
52% 942
33.1 IPS
 
Face Detection (F32)
100% 737
8.46 IPS
 
Face Detection (F16)
100% 735
8.44 IPS
 
Face Detection (I8)
75% 939
10.8 IPS
 
Text Classification (F32)
100% 1118
442.1 IPS
 
Text Classification (F16)
100% 1096
433.7 IPS
 
Machine Translation (F32)
100% 803
123.8 IPS
 
Machine Translation (F16)
100% 797
122.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download