Geekbench ML Score

4667
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

User yuyhero
Upload Date May 19 2024 06:06 AM
Views 2

System Information

System Information
Operating System iOS 17.5
Model iPad16,5
Model IDiPad16,5
Motherboard J720AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 4.41 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% 1890
353.7 IPS
 
Image Classification (F16)
100% 2541
475.5 IPS
 
Image Classification (I8)
99% 2534
474.2 IPS
 
Image Segmentation (F32)
100% 1193
19.9 IPS
 
Image Segmentation (F16)
100% 1166
19.5 IPS
 
Image Segmentation (I8)
100% 1165
19.4 IPS
 
Pose Estimation (F32)
100% 9514
11.5 IPS
 
Pose Estimation (F16)
100% 17957
21.7 IPS
 
Pose Estimation (I8)
100% 17955
21.7 IPS
 
Object Detection (F32)
100% 1919
143.3 IPS
 
Object Detection (F16)
100% 2619
195.5 IPS
 
Object Detection (I8)
97% 1922
143.5 IPS
 
Face Detection (F32)
100% 3535
42.0 IPS
 
Face Detection (F16)
97% 5605
66.6 IPS
 
Face Detection (I8)
97% 5604
66.6 IPS
 
Depth Estimation (F32)
100% 7574
58.7 IPS
 
Depth Estimation (F16)
100% 11203
86.9 IPS
 
Depth Estimation (I8)
99% 11201
86.9 IPS
 
Style Transfer (F32)
100% 23423
30.8 IPS
 
Style Transfer (F16)
100% 34471
45.3 IPS
 
Style Transfer (I8)
100% 34580
45.5 IPS
 
Image Super-Resolution (F32)
100% 5789
206.7 IPS
 
Image Super-Resolution (F16)
100% 6775
242.0 IPS
 
Image Super-Resolution (I8)
100% 6811
243.2 IPS
 
Text Classification (F32)
100% 2758
3.96 KIPS
 
Text Classification (F16)
100% 4363
6.27 KIPS
 
Text Classification (I8)
96% 4373
6.29 KIPS
 
Machine Translation (F32)
100% 1622
29.8 IPS
 
Machine Translation (F16)
100% 1866
34.3 IPS
 
Machine Translation (I8)
99% 1615
29.7 IPS
 

Compare

Set Baseline Geekbench 6 now available