Geekbench ML Score

1629
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 09:03 AM
Views 2

System Information

System Information
Operating System iOS 15.2.1
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 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1503
161.1 IPS
 
Image Classification (F16)
100% 1700
182.1 IPS
 
Image Classification (I8)
81% 641
68.7 IPS
 
Image Segmentation (F32)
100% 4235
26.2 IPS
 
Image Segmentation (F16)
100% 5845
36.1 IPS
 
Image Segmentation (I8)
89% 1172
7.24 IPS
 
Pose Estimation (F32)
100% 1489
6.02 IPS
 
Pose Estimation (F16)
100% 4979
20.1 IPS
 
Pose Estimation (I8)
80% 224
0.91 IPS
 
Object Detection (F32)
100% 1628
57.1 IPS
 
Object Detection (F16)
99% 1685
59.1 IPS
 
Object Detection (I8)
52% 915
32.1 IPS
 
Face Detection (F32)
100% 4292
49.3 IPS
 
Face Detection (F16)
97% 5345
61.4 IPS
 
Face Detection (I8)
75% 897
10.3 IPS
 
Text Classification (F32)
100% 851
336.6 IPS
 
Text Classification (F16)
98% 1094
432.5 IPS
 
Machine Translation (F32)
100% 1683
259.3 IPS
 
Machine Translation (F16)
100% 1673
257.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download