Geekbench ML Score

2718
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date April 21 2022 09:44 PM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,10
Motherboard J523AP
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 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6065
649.9 IPS
 
Image Classification (F16)
100% 6084
651.9 IPS
 
Image Classification (I8)
81% 688
73.7 IPS
 
Image Segmentation (F32)
100% 2255
13.9 IPS
 
Image Segmentation (F16)
100% 2254
13.9 IPS
 
Image Segmentation (I8)
89% 1255
7.75 IPS
 
Pose Estimation (F32)
100% 19659
79.5 IPS
 
Pose Estimation (F16)
100% 19675
79.6 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 7350
257.9 IPS
 
Object Detection (F16)
100% 7353
258.0 IPS
 
Object Detection (I8)
52% 985
34.6 IPS
 
Face Detection (F32)
100% 7850
90.2 IPS
 
Face Detection (F16)
100% 7891
90.7 IPS
 
Face Detection (I8)
75% 965
11.1 IPS
 
Text Classification (F32)
100% 1057
418.1 IPS
 
Text Classification (F16)
100% 1055
417.4 IPS
 
Machine Translation (F32)
100% 1831
282.2 IPS
 
Machine Translation (F16)
100% 1825
281.3 IPS
 

Compare

Set Baseline Geekbench 6 now available