Geekbench ML Score

4670
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 22 2024 03:02 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,5
Model IDiPad16,5
Motherboard J720AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 2.08 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 7.20 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1878
351.4 IPS
 
Image Classification (F16)
100% 2520
471.5 IPS
 
Image Classification (I8)
99% 2481
464.3 IPS
 
Image Segmentation (F32)
100% 1169
19.5 IPS
 
Image Segmentation (F16)
100% 1165
19.5 IPS
 
Image Segmentation (I8)
100% 1174
19.6 IPS
 
Pose Estimation (F32)
100% 9550
11.6 IPS
 
Pose Estimation (F16)
100% 17962
21.8 IPS
 
Pose Estimation (I8)
100% 17963
21.8 IPS
 
Object Detection (F32)
100% 1923
143.6 IPS
 
Object Detection (F16)
100% 2622
195.7 IPS
 
Object Detection (I8)
97% 1940
144.8 IPS
 
Face Detection (F32)
100% 3550
42.2 IPS
 
Face Detection (F16)
97% 5664
67.3 IPS
 
Face Detection (I8)
97% 5645
67.1 IPS
 
Depth Estimation (F32)
100% 7605
59.0 IPS
 
Depth Estimation (F16)
100% 11229
87.1 IPS
 
Depth Estimation (I8)
99% 11267
87.4 IPS
 
Style Transfer (F32)
100% 23410
30.8 IPS
 
Style Transfer (F16)
100% 34595
45.5 IPS
 
Style Transfer (I8)
100% 34727
45.7 IPS
 
Image Super-Resolution (F32)
100% 5805
207.3 IPS
 
Image Super-Resolution (F16)
100% 6765
241.6 IPS
 
Image Super-Resolution (I8)
100% 6767
241.7 IPS
 
Text Classification (F32)
100% 2733
3.93 KIPS
 
Text Classification (F16)
100% 4380
6.30 KIPS
 
Text Classification (I8)
96% 4381
6.30 KIPS
 
Machine Translation (F32)
100% 1630
30.0 IPS
 
Machine Translation (F16)
100% 1882
34.6 IPS
 
Machine Translation (I8)
99% 1620
29.8 IPS
 

Compare

Set Baseline Geekbench 6 now available