Geekbench ML Score

867
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 08:54 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
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 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 646
69.2 IPS
 
Image Classification (F16)
100% 622
66.6 IPS
 
Image Classification (I8)
81% 420
45.0 IPS
 
Image Segmentation (F32)
100% 964
5.95 IPS
 
Image Segmentation (F16)
100% 934
5.77 IPS
 
Image Segmentation (I8)
89% 1399
8.64 IPS
 
Pose Estimation (F32)
100% 359
1.45 IPS
 
Pose Estimation (F16)
100% 359
1.45 IPS
 
Pose Estimation (I8)
80% 441
1.79 IPS
 
Object Detection (F32)
100% 912
32.0 IPS
 
Object Detection (F16)
100% 917
32.2 IPS
 
Object Detection (I8)
52% 463
16.3 IPS
 
Face Detection (F32)
100% 1101
12.6 IPS
 
Face Detection (F16)
100% 1078
12.4 IPS
 
Face Detection (I8)
75% 818
9.40 IPS
 
Text Classification (F32)
100% 2261
894.3 IPS
 
Text Classification (F16)
100% 2332
922.4 IPS
 
Machine Translation (F32)
100% 1686
259.8 IPS
 
Machine Translation (F16)
100% 1679
258.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download