Geekbench ML Score

3475
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 26 2024 08:07 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad13,17
Model IDiPad13,17
Motherboard J408AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 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 7.47 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1552
290.4 IPS
 
Image Classification (F16)
100% 1589
297.4 IPS
 
Image Classification (I8)
99% 1607
300.8 IPS
 
Image Segmentation (F32)
100% 835
13.9 IPS
 
Image Segmentation (F16)
100% 842
14.1 IPS
 
Image Segmentation (I8)
100% 880
14.7 IPS
 
Pose Estimation (F32)
100% 16598
20.1 IPS
 
Pose Estimation (F16)
100% 18097
21.9 IPS
 
Pose Estimation (I8)
100% 17712
21.4 IPS
 
Object Detection (F32)
100% 1624
121.3 IPS
 
Object Detection (F16)
100% 1541
115.1 IPS
 
Object Detection (I8)
97% 1558
116.3 IPS
 
Face Detection (F32)
100% 5856
69.6 IPS
 
Face Detection (F16)
98% 7250
86.2 IPS
 
Face Detection (I8)
97% 7260
86.3 IPS
 
Depth Estimation (F32)
100% 12227
94.8 IPS
 
Depth Estimation (F16)
100% 13790
106.9 IPS
 
Depth Estimation (I8)
37% 12624
97.9 IPS
 
Style Transfer (F32)
100% 27778
36.5 IPS
 
Style Transfer (F16)
100% 30999
40.8 IPS
 
Style Transfer (I8)
100% 31990
42.1 IPS
 
Image Super-Resolution (F32)
100% 4975
177.7 IPS
 
Image Super-Resolution (F16)
100% 5448
194.6 IPS
 
Image Super-Resolution (I8)
100% 5168
184.6 IPS
 
Text Classification (F32)
100% 1180
1.70 KIPS
 
Text Classification (F16)
100% 762
1.10 KIPS
 
Text Classification (I8)
96% 766
1.10 KIPS
 
Machine Translation (F32)
100% 572
10.5 IPS
 
Machine Translation (F16)
100% 584
10.7 IPS
 
Machine Translation (I8)
99% 572
10.5 IPS
 

Compare

Set Baseline Geekbench 6 now available