Geekbench ML Score

3476
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 26 2024 12:32 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.48 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 7.31 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1482
277.3 IPS
 
Image Classification (F16)
100% 1899
355.4 IPS
 
Image Classification (I8)
99% 1887
353.0 IPS
 
Image Segmentation (F32)
100% 806
13.5 IPS
 
Image Segmentation (F16)
100% 812
13.6 IPS
 
Image Segmentation (I8)
100% 817
13.6 IPS
 
Pose Estimation (F32)
100% 5924
7.17 IPS
 
Pose Estimation (F16)
100% 13880
16.8 IPS
 
Pose Estimation (I8)
100% 13909
16.8 IPS
 
Object Detection (F32)
100% 1466
109.4 IPS
 
Object Detection (F16)
100% 2021
150.9 IPS
 
Object Detection (I8)
97% 1476
110.2 IPS
 
Face Detection (F32)
100% 2848
33.9 IPS
 
Face Detection (F16)
97% 4378
52.1 IPS
 
Face Detection (I8)
97% 4376
52.0 IPS
 
Depth Estimation (F32)
100% 5232
40.6 IPS
 
Depth Estimation (F16)
100% 8491
65.8 IPS
 
Depth Estimation (I8)
99% 8622
66.9 IPS
 
Style Transfer (F32)
100% 16709
22.0 IPS
 
Style Transfer (F16)
100% 26637
35.0 IPS
 
Style Transfer (I8)
100% 26305
34.6 IPS
 
Image Super-Resolution (F32)
100% 3790
135.4 IPS
 
Image Super-Resolution (F16)
100% 4943
176.5 IPS
 
Image Super-Resolution (I8)
100% 4878
174.2 IPS
 
Text Classification (F32)
100% 2080
2.99 KIPS
 
Text Classification (F16)
100% 3233
4.65 KIPS
 
Text Classification (I8)
96% 3232
4.65 KIPS
 
Machine Translation (F32)
100% 1277
23.5 IPS
 
Machine Translation (F16)
100% 1536
28.3 IPS
 
Machine Translation (I8)
99% 1270
23.4 IPS
 

Compare

Set Baseline Geekbench 6 now available