Geekbench ML Score

6568
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 06 2024 04:20 AM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad16,4
Model IDiPad16,4
Motherboard J718AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.41 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 15.15 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4060
759.7 IPS
 
Image Classification (F16)
100% 4393
822.1 IPS
 
Image Classification (I8)
99% 4152
777.0 IPS
 
Image Segmentation (F32)
100% 2005
33.5 IPS
 
Image Segmentation (F16)
100% 2224
37.1 IPS
 
Image Segmentation (I8)
100% 2181
36.4 IPS
 
Pose Estimation (F32)
100% 26685
32.3 IPS
 
Pose Estimation (F16)
100% 28493
34.5 IPS
 
Pose Estimation (I8)
100% 27589
33.4 IPS
 
Object Detection (F32)
100% 3402
254.0 IPS
 
Object Detection (F16)
100% 3922
292.8 IPS
 
Object Detection (I8)
97% 3156
235.7 IPS
 
Face Detection (F32)
100% 11078
131.7 IPS
 
Face Detection (F16)
98% 13705
163.0 IPS
 
Face Detection (I8)
97% 13452
159.9 IPS
 
Depth Estimation (F32)
100% 19623
152.2 IPS
 
Depth Estimation (F16)
100% 22301
172.9 IPS
 
Depth Estimation (I8)
99% 20212
156.7 IPS
 
Style Transfer (F32)
100% 55032
72.4 IPS
 
Style Transfer (F16)
100% 65496
86.2 IPS
 
Style Transfer (I8)
100% 64758
85.2 IPS
 
Image Super-Resolution (F32)
100% 8973
320.4 IPS
 
Image Super-Resolution (F16)
100% 9538
340.6 IPS
 
Image Super-Resolution (I8)
100% 8487
303.1 IPS
 
Text Classification (F32)
100% 1489
2.14 KIPS
 
Text Classification (F16)
100% 1818
2.61 KIPS
 
Text Classification (I8)
96% 529
759.8 IPS
 
Machine Translation (F32)
100% 1059
19.5 IPS
 
Machine Translation (F16)
100% 1122
20.7 IPS
 
Machine Translation (I8)
99% 1006
18.5 IPS
 

Compare

Set Baseline Geekbench 6 now available