Geekbench ML Score

4477
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 06:21 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad mini (6th generation)
Model IDiPad14,1
Motherboard J310AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 GHz
Cluster 12 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 3.78 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 528
98.8 IPS
 
Image Classification (F16)
100% 4984
932.7 IPS
 
Image Classification (I8)
99% 5093
953.1 IPS
 
Image Segmentation (F32)
100% 1056
17.6 IPS
 
Image Segmentation (F16)
100% 1663
27.8 IPS
 
Image Segmentation (I8)
100% 1646
27.5 IPS
 
Pose Estimation (F32)
100% 10268
12.4 IPS
 
Pose Estimation (F16)
100% 68049
82.4 IPS
 
Pose Estimation (I8)
100% 68298
82.7 IPS
 
Object Detection (F32)
100% 724
54.0 IPS
 
Object Detection (F16)
100% 3583
267.5 IPS
 
Object Detection (I8)
97% 848
63.3 IPS
 
Face Detection (F32)
100% 3277
39.0 IPS
 
Face Detection (F16)
97% 9394
111.7 IPS
 
Face Detection (I8)
96% 9359
111.3 IPS
 
Depth Estimation (F32)
100% 7036
54.6 IPS
 
Depth Estimation (F16)
100% 32516
252.2 IPS
 
Depth Estimation (I8)
37% 37878
293.7 IPS
 
Style Transfer (F32)
100% 18419
24.2 IPS
 
Style Transfer (F16)
100% 93947
123.6 IPS
 
Style Transfer (I8)
100% 95103
125.1 IPS
 
Image Super-Resolution (F32)
100% 2724
97.3 IPS
 
Image Super-Resolution (F16)
100% 14288
510.3 IPS
 
Image Super-Resolution (I8)
100% 13956
498.4 IPS
 
Text Classification (F32)
100% 411
591.4 IPS
 
Text Classification (F16)
100% 1008
1.45 KIPS
 
Text Classification (I8)
96% 406
584.1 IPS
 
Machine Translation (F32)
100% 450
8.27 IPS
 
Machine Translation (F16)
100% 1198
22.0 IPS
 
Machine Translation (I8)
99% 414
7.61 IPS
 

Compare

Set Baseline Geekbench 6 now available