Geekbench ML Score

2809
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:12 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.35 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6819
730.6 IPS
 
Image Classification (F16)
100% 6790
727.5 IPS
 
Image Classification (I8)
81% 681
73.0 IPS
 
Image Segmentation (F32)
100% 2088
12.9 IPS
 
Image Segmentation (F16)
100% 2088
12.9 IPS
 
Image Segmentation (I8)
89% 1236
7.63 IPS
 
Pose Estimation (F32)
100% 19599
79.3 IPS
 
Pose Estimation (F16)
100% 19594
79.3 IPS
 
Pose Estimation (I8)
80% 236
0.96 IPS
 
Object Detection (F32)
100% 8003
280.9 IPS
 
Object Detection (F16)
100% 7992
280.5 IPS
 
Object Detection (I8)
52% 969
34.0 IPS
 
Face Detection (F32)
100% 8661
99.5 IPS
 
Face Detection (F16)
100% 8593
98.7 IPS
 
Face Detection (I8)
75% 948
10.9 IPS
 
Text Classification (F32)
100% 1208
477.9 IPS
 
Text Classification (F16)
100% 1200
474.5 IPS
 
Machine Translation (F32)
100% 1852
285.4 IPS
 
Machine Translation (F16)
100% 1849
285.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download