Geekbench ML Score

1032
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:42 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,11
Motherboard J523xAP
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 15.34 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 941
100.8 IPS
 
Image Classification (F16)
100% 945
101.2 IPS
 
Image Classification (I8)
81% 404
43.2 IPS
 
Image Segmentation (F32)
100% 1350
8.34 IPS
 
Image Segmentation (F16)
100% 1350
8.34 IPS
 
Image Segmentation (I8)
89% 1490
9.21 IPS
 
Pose Estimation (F32)
100% 640
2.59 IPS
 
Pose Estimation (F16)
100% 640
2.59 IPS
 
Pose Estimation (I8)
80% 787
3.18 IPS
 
Object Detection (F32)
100% 1445
50.7 IPS
 
Object Detection (F16)
100% 1454
51.0 IPS
 
Object Detection (I8)
52% 650
22.8 IPS
 
Face Detection (F32)
100% 1693
19.4 IPS
 
Face Detection (F16)
100% 1683
19.3 IPS
 
Face Detection (I8)
75% 812
9.33 IPS
 
Text Classification (F32)
100% 707
279.6 IPS
 
Text Classification (F16)
100% 834
329.7 IPS
 
Machine Translation (F32)
100% 1707
263.1 IPS
 
Machine Translation (F16)
100% 1847
284.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download