Geekbench ML Score

5916
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 13 2024 02:05 PM
Views 3

System Information

System Information
Operating System iOS 18.0
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 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 7.35 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3370
630.6 IPS
 
Image Classification (F16)
100% 3371
630.8 IPS
 
Image Classification (I8)
99% 3013
563.8 IPS
 
Image Segmentation (F32)
100% 1422
23.8 IPS
 
Image Segmentation (F16)
100% 1517
25.3 IPS
 
Image Segmentation (I8)
100% 1516
25.3 IPS
 
Pose Estimation (F32)
100% 23582
28.6 IPS
 
Pose Estimation (F16)
100% 25138
30.4 IPS
 
Pose Estimation (I8)
100% 24341
29.5 IPS
 
Object Detection (F32)
100% 2845
212.4 IPS
 
Object Detection (F16)
100% 2907
217.0 IPS
 
Object Detection (I8)
97% 2651
197.9 IPS
 
Face Detection (F32)
100% 8893
105.7 IPS
 
Face Detection (F16)
98% 10043
119.4 IPS
 
Face Detection (I8)
97% 9832
116.9 IPS
 
Depth Estimation (F32)
100% 16369
126.9 IPS
 
Depth Estimation (F16)
100% 17428
135.2 IPS
 
Depth Estimation (I8)
99% 15748
122.1 IPS
 
Style Transfer (F32)
100% 38761
51.0 IPS
 
Style Transfer (F16)
100% 42392
55.8 IPS
 
Style Transfer (I8)
100% 45898
60.4 IPS
 
Image Super-Resolution (F32)
100% 9578
342.0 IPS
 
Image Super-Resolution (F16)
100% 10412
371.9 IPS
 
Image Super-Resolution (I8)
100% 9820
350.7 IPS
 
Text Classification (F32)
100% 2026
2.91 KIPS
 
Text Classification (F16)
100% 3480
5.00 KIPS
 
Text Classification (I8)
96% 3436
4.94 KIPS
 
Machine Translation (F32)
100% 853
15.7 IPS
 
Machine Translation (F16)
100% 862
15.9 IPS
 
Machine Translation (I8)
99% 788
14.5 IPS
 

Compare

Set Baseline Geekbench 6 now available