Geekbench ML Score

3485
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 17 2024 05:48 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad14,8
Model IDiPad14,8
Motherboard J507AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 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 7.47 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1504
281.4 IPS
 
Image Classification (F16)
100% 1892
354.0 IPS
 
Image Classification (I8)
99% 1894
354.4 IPS
 
Image Segmentation (F32)
100% 789
13.2 IPS
 
Image Segmentation (F16)
100% 791
13.2 IPS
 
Image Segmentation (I8)
100% 793
13.2 IPS
 
Pose Estimation (F32)
100% 5906
7.15 IPS
 
Pose Estimation (F16)
100% 14027
17.0 IPS
 
Pose Estimation (I8)
100% 13954
16.9 IPS
 
Object Detection (F32)
100% 1498
111.9 IPS
 
Object Detection (F16)
100% 2052
153.2 IPS
 
Object Detection (I8)
97% 1504
112.3 IPS
 
Face Detection (F32)
100% 2850
33.9 IPS
 
Face Detection (F16)
97% 4397
52.3 IPS
 
Face Detection (I8)
97% 4397
52.3 IPS
 
Depth Estimation (F32)
100% 5367
41.6 IPS
 
Depth Estimation (F16)
100% 8720
67.6 IPS
 
Depth Estimation (I8)
99% 8713
67.6 IPS
 
Style Transfer (F32)
100% 16982
22.3 IPS
 
Style Transfer (F16)
100% 26583
35.0 IPS
 
Style Transfer (I8)
100% 26574
35.0 IPS
 
Image Super-Resolution (F32)
100% 3769
134.6 IPS
 
Image Super-Resolution (F16)
100% 4894
174.8 IPS
 
Image Super-Resolution (I8)
100% 4848
173.2 IPS
 
Text Classification (F32)
100% 2118
3.04 KIPS
 
Text Classification (F16)
100% 3243
4.66 KIPS
 
Text Classification (I8)
96% 3252
4.67 KIPS
 
Machine Translation (F32)
100% 1256
23.1 IPS
 
Machine Translation (F16)
100% 1541
28.4 IPS
 
Machine Translation (I8)
99% 1250
23.0 IPS
 

Compare

Set Baseline Geekbench 6 now available