Geekbench ML Score

636
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:15 PM
Views 1

System Information

System Information
Operating System iOS 14.7.1
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 389
41.7 IPS
 
Image Classification (F16)
100% 386
41.3 IPS
 
Image Classification (I8)
81% 805
86.3 IPS
 
Image Segmentation (F32)
100% 496
3.07 IPS
 
Image Segmentation (F16)
100% 502
3.10 IPS
 
Image Segmentation (I8)
89% 1277
7.89 IPS
 
Pose Estimation (F32)
100% 241
0.98 IPS
 
Pose Estimation (F16)
100% 300
1.21 IPS
 
Pose Estimation (I8)
80% 362
1.47 IPS
 
Object Detection (F32)
100% 629
22.1 IPS
 
Object Detection (F16)
100% 625
21.9 IPS
 
Object Detection (I8)
52% 943
33.1 IPS
 
Face Detection (F32)
100% 734
8.43 IPS
 
Face Detection (F16)
100% 744
8.55 IPS
 
Face Detection (I8)
75% 971
11.2 IPS
 
Text Classification (F32)
100% 1238
489.7 IPS
 
Text Classification (F16)
100% 1209
478.3 IPS
 
Machine Translation (F32)
100% 794
122.3 IPS
 
Machine Translation (F16)
100% 800
123.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download