Geekbench ML Score

1377
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 09:53 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1180
126.4 IPS
 
Image Classification (F16)
100% 1565
167.6 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 3453
21.3 IPS
 
Image Segmentation (F16)
100% 5400
33.4 IPS
 
Image Segmentation (I8)
89% 830
5.13 IPS
 
Pose Estimation (F32)
100% 1423
5.76 IPS
 
Pose Estimation (F16)
100% 4439
18.0 IPS
 
Pose Estimation (I8)
80% 152
0.61 IPS
 
Object Detection (F32)
100% 1500
52.7 IPS
 
Object Detection (F16)
99% 1862
65.3 IPS
 
Object Detection (I8)
52% 637
22.4 IPS
 
Face Detection (F32)
100% 3622
41.6 IPS
 
Face Detection (F16)
97% 5447
62.6 IPS
 
Face Detection (I8)
75% 634
7.28 IPS
 
Text Classification (F32)
100% 957
378.4 IPS
 
Text Classification (F16)
98% 1198
473.9 IPS
 
Machine Translation (F32)
100% 1185
182.7 IPS
 
Machine Translation (F16)
100% 1172
180.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download