Geekbench ML Score

2628
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 03 2021 04:31 PM
Views 1

System Information

System Information
Operating System iOS 14.6
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,6
Motherboard J518AP
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 7.24 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5504
589.7 IPS
 
Image Classification (F16)
100% 5503
589.6 IPS
 
Image Classification (I8)
81% 688
73.7 IPS
 
Image Segmentation (F32)
100% 2161
13.3 IPS
 
Image Segmentation (F16)
100% 2190
13.5 IPS
 
Image Segmentation (I8)
89% 1243
7.68 IPS
 
Pose Estimation (F32)
100% 19622
79.4 IPS
 
Pose Estimation (F16)
100% 19228
77.8 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 7152
251.0 IPS
 
Object Detection (F16)
100% 6978
244.9 IPS
 
Object Detection (I8)
52% 986
34.6 IPS
 
Face Detection (F32)
100% 7210
82.8 IPS
 
Face Detection (F16)
100% 7227
83.0 IPS
 
Face Detection (I8)
75% 961
11.0 IPS
 
Text Classification (F32)
100% 1006
398.1 IPS
 
Text Classification (F16)
100% 1011
400.0 IPS
 
Machine Translation (F32)
100% 1843
284.0 IPS
 
Machine Translation (F16)
100% 1842
283.9 IPS
 

Compare

Set Baseline Geekbench 6 now available