Geekbench ML Score

2620
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 31 2023 04:01 AM
Views 1

System Information

System Information
Operating System iOS 16.4.1
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4663
499.6 IPS
 
Image Classification (F16)
100% 4651
498.3 IPS
 
Image Classification (I8)
81% 688
73.8 IPS
 
Image Segmentation (F32)
100% 2107
13.0 IPS
 
Image Segmentation (F16)
100% 2076
12.8 IPS
 
Image Segmentation (I8)
89% 1236
7.63 IPS
 
Pose Estimation (F32)
100% 19412
78.5 IPS
 
Pose Estimation (F16)
100% 19452
78.7 IPS
 
Pose Estimation (I8)
80% 236
0.95 IPS
 
Object Detection (F32)
100% 6223
218.4 IPS
 
Object Detection (F16)
100% 6117
214.7 IPS
 
Object Detection (I8)
52% 971
34.1 IPS
 
Face Detection (F32)
100% 8545
98.2 IPS
 
Face Detection (F16)
100% 8579
98.6 IPS
 
Face Detection (I8)
75% 953
11.0 IPS
 
Text Classification (F32)
100% 1212
479.2 IPS
 
Text Classification (F16)
100% 1196
473.0 IPS
 
Machine Translation (F32)
100% 1814
279.6 IPS
 
Machine Translation (F16)
100% 1818
280.2 IPS
 

Compare

Set Baseline Geekbench 6 now available