Geekbench ML Score

2702
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 14 2022 07:41 PM
Views 8

System Information

System Information
Operating System iOS 15.7
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 7.34 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6003
643.2 IPS
 
Image Classification (F16)
100% 5991
641.9 IPS
 
Image Classification (I8)
81% 687
73.6 IPS
 
Image Segmentation (F32)
100% 2241
13.8 IPS
 
Image Segmentation (F16)
100% 2253
13.9 IPS
 
Image Segmentation (I8)
89% 1257
7.76 IPS
 
Pose Estimation (F32)
100% 19038
77.0 IPS
 
Pose Estimation (F16)
100% 18951
76.7 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 7271
255.2 IPS
 
Object Detection (F16)
100% 7320
256.9 IPS
 
Object Detection (I8)
52% 987
34.6 IPS
 
Face Detection (F32)
100% 7851
90.2 IPS
 
Face Detection (F16)
100% 7870
90.4 IPS
 
Face Detection (I8)
75% 965
11.1 IPS
 
Text Classification (F32)
100% 1049
414.9 IPS
 
Text Classification (F16)
100% 1058
418.5 IPS
 
Machine Translation (F32)
100% 1838
283.3 IPS
 
Machine Translation (F16)
100% 1837
283.1 IPS
 

Compare

Set Baseline Geekbench 6 now available