Geekbench ML Score

2415
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:52 PM
Views 1

System Information

System Information
Operating System iOS 15.2.1
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
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 3.63 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5160
552.9 IPS
 
Image Classification (F16)
100% 5067
542.9 IPS
 
Image Classification (I8)
81% 642
68.7 IPS
 
Image Segmentation (F32)
100% 1884
11.6 IPS
 
Image Segmentation (F16)
100% 1897
11.7 IPS
 
Image Segmentation (I8)
89% 1108
6.85 IPS
 
Pose Estimation (F32)
100% 17664
71.5 IPS
 
Pose Estimation (F16)
100% 17085
69.1 IPS
 
Pose Estimation (I8)
80% 217
0.88 IPS
 
Object Detection (F32)
100% 6323
221.9 IPS
 
Object Detection (F16)
100% 6419
225.3 IPS
 
Object Detection (I8)
52% 859
30.1 IPS
 
Face Detection (F32)
100% 6858
78.8 IPS
 
Face Detection (F16)
100% 6839
78.6 IPS
 
Face Detection (I8)
75% 877
10.1 IPS
 
Text Classification (F32)
100% 1038
410.4 IPS
 
Text Classification (F16)
100% 1036
409.9 IPS
 
Machine Translation (F32)
100% 1686
259.9 IPS
 
Machine Translation (F16)
100% 1677
258.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download