Geekbench ML Score

1417
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 01:37 AM
Views 1

System Information

System Information
Operating System iOS 15.7
Model iPad Air (3rd generation)
Model IDiPad11,4
Motherboard J218AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.84 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3981
426.6 IPS
 
Image Classification (F16)
100% 3931
421.1 IPS
 
Image Classification (I8)
81% 403
43.2 IPS
 
Image Segmentation (F32)
100% 1395
8.62 IPS
 
Image Segmentation (F16)
100% 1410
8.71 IPS
 
Image Segmentation (I8)
89% 747
4.61 IPS
 
Pose Estimation (F32)
100% 7455
30.2 IPS
 
Pose Estimation (F16)
100% 7357
29.8 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
94% 4062
142.6 IPS
 
Object Detection (F16)
94% 4095
143.7 IPS
 
Object Detection (I8)
52% 568
19.9 IPS
 
Face Detection (F32)
67% 3859
44.3 IPS
 
Face Detection (F16)
67% 3872
44.5 IPS
 
Face Detection (I8)
75% 547
6.29 IPS
 
Text Classification (F32)
100% 382
151.3 IPS
 
Text Classification (F16)
100% 355
140.3 IPS
 
Machine Translation (F32)
100% 1001
154.3 IPS
 
Machine Translation (F16)
100% 1001
154.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download