Geekbench ML Score

5298
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 18 2024 09:05 PM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.40 GHz
Cluster 14 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 15.07 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2022
378.4 IPS
 
Image Classification (F16)
100% 3303
618.0 IPS
 
Image Classification (I8)
99% 3335
624.1 IPS
 
Image Segmentation (F32)
100% 1340
22.4 IPS
 
Image Segmentation (F16)
100% 1738
29.0 IPS
 
Image Segmentation (I8)
100% 1752
29.3 IPS
 
Pose Estimation (F32)
100% 9649
11.7 IPS
 
Pose Estimation (F16)
100% 18220
22.1 IPS
 
Pose Estimation (I8)
100% 18221
22.1 IPS
 
Object Detection (F32)
100% 2090
156.0 IPS
 
Object Detection (F16)
100% 3205
239.3 IPS
 
Object Detection (I8)
97% 2086
155.8 IPS
 
Face Detection (F32)
100% 3923
46.6 IPS
 
Face Detection (F16)
97% 7476
88.9 IPS
 
Face Detection (I8)
97% 7446
88.5 IPS
 
Depth Estimation (F32)
100% 8275
64.2 IPS
 
Depth Estimation (F16)
100% 14694
114.0 IPS
 
Depth Estimation (I8)
99% 14746
114.4 IPS
 
Style Transfer (F32)
100% 24603
32.4 IPS
 
Style Transfer (F16)
100% 37542
49.4 IPS
 
Style Transfer (I8)
100% 37472
49.3 IPS
 
Image Super-Resolution (F32)
100% 5924
211.5 IPS
 
Image Super-Resolution (F16)
100% 6883
245.8 IPS
 
Image Super-Resolution (I8)
100% 6909
246.7 IPS
 
Text Classification (F32)
100% 2689
3.86 KIPS
 
Text Classification (F16)
100% 4772
6.86 KIPS
 
Text Classification (I8)
96% 4773
6.86 KIPS
 
Machine Translation (F32)
100% 1690
31.1 IPS
 
Machine Translation (F16)
100% 1986
36.6 IPS
 
Machine Translation (I8)
99% 1661
30.6 IPS
 

Compare

Set Baseline Geekbench 6 now available