Geekbench ML Score

740
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 09:20 AM
Views 1

System Information

System Information
Operating System iOS 14.7.1
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
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 5.58 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 633
67.8 IPS
 
Image Classification (F16)
100% 627
67.2 IPS
 
Image Classification (I8)
81% 293
31.4 IPS
 
Image Segmentation (F32)
100% 975
6.02 IPS
 
Image Segmentation (F16)
100% 956
5.90 IPS
 
Image Segmentation (I8)
89% 1306
8.07 IPS
 
Pose Estimation (F32)
100% 337
1.36 IPS
 
Pose Estimation (F16)
100% 331
1.34 IPS
 
Pose Estimation (I8)
80% 434
1.76 IPS
 
Object Detection (F32)
100% 946
33.2 IPS
 
Object Detection (F16)
100% 946
33.2 IPS
 
Object Detection (I8)
52% 516
18.1 IPS
 
Face Detection (F32)
100% 1131
13.0 IPS
 
Face Detection (F16)
100% 1094
12.6 IPS
 
Face Detection (I8)
75% 716
8.22 IPS
 
Text Classification (F32)
100% 688
272.2 IPS
 
Text Classification (F16)
100% 598
236.7 IPS
 
Machine Translation (F32)
100% 1706
262.9 IPS
 
Machine Translation (F16)
100% 1708
263.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download