Geekbench ML Score

3447
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

User Reghir
Upload Date May 08 2024 11:07 AM
Views 5

System Information

System Information
Operating System iOS 17.4.1
Model iPad14,4
Model IDiPad14,4
Motherboard J618AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.48 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1496
280.0 IPS
 
Image Classification (F16)
100% 1902
355.9 IPS
 
Image Classification (I8)
99% 1891
353.9 IPS
 
Image Segmentation (F32)
100% 795
13.3 IPS
 
Image Segmentation (F16)
100% 785
13.1 IPS
 
Image Segmentation (I8)
100% 783
13.1 IPS
 
Pose Estimation (F32)
100% 5912
7.16 IPS
 
Pose Estimation (F16)
100% 14008
17.0 IPS
 
Pose Estimation (I8)
100% 14054
17.0 IPS
 
Object Detection (F32)
100% 1464
109.3 IPS
 
Object Detection (F16)
100% 1999
149.2 IPS
 
Object Detection (I8)
97% 1459
108.9 IPS
 
Face Detection (F32)
100% 2834
33.7 IPS
 
Face Detection (F16)
97% 4354
51.8 IPS
 
Face Detection (I8)
97% 4343
51.6 IPS
 
Depth Estimation (F32)
100% 5348
41.5 IPS
 
Depth Estimation (F16)
100% 8591
66.6 IPS
 
Depth Estimation (I8)
99% 8568
66.4 IPS
 
Style Transfer (F32)
100% 16956
22.3 IPS
 
Style Transfer (F16)
100% 26492
34.8 IPS
 
Style Transfer (I8)
100% 26423
34.8 IPS
 
Image Super-Resolution (F32)
100% 3815
136.3 IPS
 
Image Super-Resolution (F16)
100% 4892
174.7 IPS
 
Image Super-Resolution (I8)
100% 4870
173.9 IPS
 
Text Classification (F32)
100% 2084
3.00 KIPS
 
Text Classification (F16)
100% 2949
4.24 KIPS
 
Text Classification (I8)
96% 2955
4.25 KIPS
 
Machine Translation (F32)
100% 1269
23.3 IPS
 
Machine Translation (F16)
100% 1542
28.4 IPS
 
Machine Translation (I8)
99% 1259
23.2 IPS
 

Compare

Set Baseline Geekbench 6 now available