Geekbench ML Score

736
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:30 PM
Views 1

System Information

System Information
Operating System iOS 15.2
Model iPhone 11
Model IDiPhone12,1
Motherboard N104AP
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 3.76 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 548
58.7 IPS
 
Image Classification (F16)
100% 541
57.9 IPS
 
Image Classification (I8)
81% 319
34.1 IPS
 
Image Segmentation (F32)
100% 872
5.39 IPS
 
Image Segmentation (F16)
100% 861
5.32 IPS
 
Image Segmentation (I8)
89% 1107
6.84 IPS
 
Pose Estimation (F32)
100% 276
1.12 IPS
 
Pose Estimation (F16)
100% 274
1.11 IPS
 
Pose Estimation (I8)
80% 338
1.37 IPS
 
Object Detection (F32)
100% 791
27.7 IPS
 
Object Detection (F16)
100% 793
27.8 IPS
 
Object Detection (I8)
52% 608
21.4 IPS
 
Face Detection (F32)
100% 1000
11.5 IPS
 
Face Detection (F16)
100% 990
11.4 IPS
 
Face Detection (I8)
75% 718
8.25 IPS
 
Text Classification (F32)
100% 1997
789.9 IPS
 
Text Classification (F16)
100% 1991
787.6 IPS
 
Machine Translation (F32)
100% 1158
178.5 IPS
 
Machine Translation (F16)
100% 1198
184.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download