Geekbench ML Score

6475
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 18 2024 09:07 PM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.40 GHz
Cluster 14 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.07 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3957
740.5 IPS
 
Image Classification (F16)
100% 4280
800.9 IPS
 
Image Classification (I8)
99% 3900
729.8 IPS
 
Image Segmentation (F32)
100% 1986
33.2 IPS
 
Image Segmentation (F16)
100% 2272
38.0 IPS
 
Image Segmentation (I8)
100% 2251
37.6 IPS
 
Pose Estimation (F32)
100% 26844
32.5 IPS
 
Pose Estimation (F16)
100% 28546
34.6 IPS
 
Pose Estimation (I8)
100% 27599
33.4 IPS
 
Object Detection (F32)
100% 3637
271.5 IPS
 
Object Detection (F16)
100% 3870
288.9 IPS
 
Object Detection (I8)
97% 3332
248.7 IPS
 
Face Detection (F32)
100% 11088
131.8 IPS
 
Face Detection (F16)
98% 13815
164.3 IPS
 
Face Detection (I8)
97% 13400
159.3 IPS
 
Depth Estimation (F32)
100% 19771
153.3 IPS
 
Depth Estimation (F16)
100% 21604
167.5 IPS
 
Depth Estimation (I8)
99% 19734
153.0 IPS
 
Style Transfer (F32)
100% 55827
73.4 IPS
 
Style Transfer (F16)
100% 64881
85.3 IPS
 
Style Transfer (I8)
100% 64553
84.9 IPS
 
Image Super-Resolution (F32)
100% 8782
313.6 IPS
 
Image Super-Resolution (F16)
100% 8398
299.9 IPS
 
Image Super-Resolution (I8)
100% 8201
292.9 IPS
 
Text Classification (F32)
100% 1509
2.17 KIPS
 
Text Classification (F16)
100% 1585
2.28 KIPS
 
Text Classification (I8)
96% 513
737.7 IPS
 
Machine Translation (F32)
100% 1053
19.4 IPS
 
Machine Translation (F16)
100% 1099
20.2 IPS
 
Machine Translation (I8)
99% 943
17.3 IPS
 

Compare

Set Baseline Geekbench 6 now available