Geekbench ML Score

1595
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:58 PM
Views 1

System Information

System Information
Operating System iOS 15.1.1
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% 1351
144.8 IPS
 
Image Classification (F16)
100% 1341
143.7 IPS
 
Image Classification (I8)
81% 644
68.9 IPS
 
Image Segmentation (F32)
100% 4055
25.0 IPS
 
Image Segmentation (F16)
100% 5795
35.8 IPS
 
Image Segmentation (I8)
89% 1174
7.25 IPS
 
Pose Estimation (F32)
100% 1468
5.94 IPS
 
Pose Estimation (F16)
100% 4856
19.6 IPS
 
Pose Estimation (I8)
80% 220
0.89 IPS
 
Object Detection (F32)
100% 1658
58.2 IPS
 
Object Detection (F16)
99% 1692
59.4 IPS
 
Object Detection (I8)
52% 920
32.3 IPS
 
Face Detection (F32)
100% 4195
48.2 IPS
 
Face Detection (F16)
97% 5421
62.3 IPS
 
Face Detection (I8)
75% 898
10.3 IPS
 
Text Classification (F32)
100% 850
336.0 IPS
 
Text Classification (F16)
98% 1097
434.0 IPS
 
Machine Translation (F32)
100% 1697
261.6 IPS
 
Machine Translation (F16)
100% 1704
262.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download