Geekbench ML Score

885
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 10:12 AM
Views 1

System Information

System Information
Operating System iOS 14.8
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% 640
68.6 IPS
 
Image Classification (F16)
100% 613
65.6 IPS
 
Image Classification (I8)
81% 443
47.5 IPS
 
Image Segmentation (F32)
100% 959
5.93 IPS
 
Image Segmentation (F16)
100% 940
5.81 IPS
 
Image Segmentation (I8)
89% 1401
8.65 IPS
 
Pose Estimation (F32)
100% 361
1.46 IPS
 
Pose Estimation (F16)
100% 355
1.44 IPS
 
Pose Estimation (I8)
80% 435
1.76 IPS
 
Object Detection (F32)
100% 870
30.5 IPS
 
Object Detection (F16)
100% 876
30.7 IPS
 
Object Detection (I8)
52% 745
26.2 IPS
 
Face Detection (F32)
100% 1075
12.3 IPS
 
Face Detection (F16)
100% 1048
12.0 IPS
 
Face Detection (I8)
75% 815
9.37 IPS
 
Text Classification (F32)
100% 2348
928.7 IPS
 
Text Classification (F16)
100% 2343
926.6 IPS
 
Machine Translation (F32)
100% 1684
259.6 IPS
 
Machine Translation (F16)
100% 1693
260.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download