Geekbench ML Score

5220
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 25 2024 08:46 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.47 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 7.31 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3386
633.6 IPS
 
Image Classification (F16)
100% 3372
630.9 IPS
 
Image Classification (I8)
99% 3031
567.1 IPS
 
Image Segmentation (F32)
100% 1447
24.2 IPS
 
Image Segmentation (F16)
100% 1524
25.5 IPS
 
Image Segmentation (I8)
100% 1531
25.6 IPS
 
Pose Estimation (F32)
100% 23495
28.5 IPS
 
Pose Estimation (F16)
100% 24993
30.3 IPS
 
Pose Estimation (I8)
100% 24369
29.5 IPS
 
Object Detection (F32)
100% 2823
210.8 IPS
 
Object Detection (F16)
100% 2858
213.3 IPS
 
Object Detection (I8)
97% 2590
193.4 IPS
 
Face Detection (F32)
100% 9341
111.1 IPS
 
Face Detection (F16)
98% 10596
126.0 IPS
 
Face Detection (I8)
97% 10118
120.3 IPS
 
Depth Estimation (F32)
100% 16450
127.6 IPS
 
Depth Estimation (F16)
100% 17588
136.4 IPS
 
Depth Estimation (I8)
37% 16248
126.0 IPS
 
Style Transfer (F32)
100% 41126
54.1 IPS
 
Style Transfer (F16)
100% 46967
61.8 IPS
 
Style Transfer (I8)
100% 43130
56.7 IPS
 
Image Super-Resolution (F32)
100% 9473
338.3 IPS
 
Image Super-Resolution (F16)
100% 10338
369.2 IPS
 
Image Super-Resolution (I8)
100% 7963
284.4 IPS
 
Text Classification (F32)
100% 1127
1.62 KIPS
 
Text Classification (F16)
100% 737
1.06 KIPS
 
Text Classification (I8)
96% 739
1.06 KIPS
 
Machine Translation (F32)
100% 808
14.9 IPS
 
Machine Translation (F16)
100% 827
15.2 IPS
 
Machine Translation (I8)
99% 776
14.3 IPS
 

Compare

Set Baseline Geekbench 6 now available