Geekbench ML Score

8884
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 01 2024 08:36 PM
Views 3

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,3
Model IDiPad16,3
Motherboard J717AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 4.41 GHz
Cluster 13 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 7.28 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4154
777.3 IPS
 
Image Classification (F16)
100% 8224
1.54 KIPS
 
Image Classification (I8)
99% 9142
1.71 KIPS
 
Image Segmentation (F32)
100% 1897
31.7 IPS
 
Image Segmentation (F16)
100% 2259
37.7 IPS
 
Image Segmentation (I8)
100% 2325
38.8 IPS
 
Pose Estimation (F32)
100% 26624
32.2 IPS
 
Pose Estimation (F16)
100% 100691
121.9 IPS
 
Pose Estimation (I8)
100% 99489
120.5 IPS
 
Object Detection (F32)
100% 2780
207.6 IPS
 
Object Detection (F16)
100% 5976
446.2 IPS
 
Object Detection (I8)
97% 3076
229.6 IPS
 
Face Detection (F32)
100% 11266
134.0 IPS
 
Face Detection (F16)
97% 13526
160.8 IPS
 
Face Detection (I8)
96% 13637
162.1 IPS
 
Depth Estimation (F32)
100% 19586
151.9 IPS
 
Depth Estimation (F16)
100% 45498
352.8 IPS
 
Depth Estimation (I8)
37% 45881
355.8 IPS
 
Style Transfer (F32)
100% 53719
70.7 IPS
 
Style Transfer (F16)
100% 152411
200.5 IPS
 
Style Transfer (I8)
100% 151450
199.2 IPS
 
Image Super-Resolution (F32)
100% 7614
271.9 IPS
 
Image Super-Resolution (F16)
100% 20504
732.3 IPS
 
Image Super-Resolution (I8)
100% 20907
746.7 IPS
 
Text Classification (F32)
100% 1387
1.99 KIPS
 
Text Classification (F16)
100% 1504
2.16 KIPS
 
Text Classification (I8)
96% 1032
1.48 KIPS
 
Machine Translation (F32)
100% 706
13.0 IPS
 
Machine Translation (F16)
100% 1831
33.7 IPS
 
Machine Translation (I8)
99% 708
13.0 IPS
 

Compare

Set Baseline Geekbench 6 now available