Geekbench ML Score

2688
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 03 2023 12:44 AM
Views 3

System Information

System Information
Operating System iOS 16.3.1
Model iPad mini (6th generation)
Model IDiPad14,1
Motherboard J310AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.78 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5678
608.4 IPS
 
Image Classification (F16)
100% 5628
603.1 IPS
 
Image Classification (I8)
81% 633
67.8 IPS
 
Image Segmentation (F32)
100% 2063
12.7 IPS
 
Image Segmentation (F16)
100% 2021
12.5 IPS
 
Image Segmentation (I8)
89% 1153
7.12 IPS
 
Pose Estimation (F32)
100% 20709
83.8 IPS
 
Pose Estimation (F16)
100% 20349
82.3 IPS
 
Pose Estimation (I8)
80% 219
0.89 IPS
 
Object Detection (F32)
100% 7038
247.0 IPS
 
Object Detection (F16)
100% 7242
254.1 IPS
 
Object Detection (I8)
52% 906
31.8 IPS
 
Face Detection (F32)
100% 8523
97.9 IPS
 
Face Detection (F16)
100% 8546
98.2 IPS
 
Face Detection (I8)
75% 887
10.2 IPS
 
Text Classification (F32)
100% 1209
478.3 IPS
 
Text Classification (F16)
100% 1214
480.3 IPS
 
Machine Translation (F32)
100% 1926
296.8 IPS
 
Machine Translation (F16)
100% 1912
294.8 IPS
 

Compare

Set Baseline Geekbench 6 now available