Geekbench ML Score

728
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 09:23 AM
Views 1

System Information

System Information
Operating System iOS 16.3
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 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 612
65.6 IPS
 
Image Classification (F16)
100% 622
66.6 IPS
 
Image Classification (I8)
81% 406
43.5 IPS
 
Image Segmentation (F32)
100% 1005
6.21 IPS
 
Image Segmentation (F16)
100% 994
6.14 IPS
 
Image Segmentation (I8)
89% 1395
8.62 IPS
 
Pose Estimation (F32)
100% 254
1.03 IPS
 
Pose Estimation (F16)
100% 341
1.38 IPS
 
Pose Estimation (I8)
80% 445
1.80 IPS
 
Object Detection (F32)
100% 876
30.7 IPS
 
Object Detection (F16)
100% 611
21.4 IPS
 
Object Detection (I8)
52% 687
24.1 IPS
 
Face Detection (F32)
100% 753
8.66 IPS
 
Face Detection (F16)
100% 995
11.4 IPS
 
Face Detection (I8)
75% 757
8.70 IPS
 
Text Classification (F32)
100% 871
344.3 IPS
 
Text Classification (F16)
100% 638
252.4 IPS
 
Machine Translation (F32)
100% 1514
233.4 IPS
 
Machine Translation (F16)
100% 1665
256.6 IPS
 

Compare

Set Baseline