Upload Date | September 20 2025 06:21 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1987
369.5 IPS |
|
Image Classification (HP)
|
100% |
14765
2.75 KIPS |
|
Image Classification (Q)
|
97% |
19132
3.57 KIPS |
|
Image Segmentation (SP)
|
100% |
1766
28.6 IPS |
|
Image Segmentation (HP)
|
100% |
18144
294.1 IPS |
|
Image Segmentation (Q)
|
99% |
23685
384.0 IPS |
|
Pose Estimation (SP)
|
100% |
9180
10.7 IPS |
|
Pose Estimation (HP)
|
100% |
151430
176.7 IPS |
|
Pose Estimation (Q)
|
95% |
289760
339.6 IPS |
|
Object Detection (SP)
|
100% |
2333
185.1 IPS |
|
Object Detection (HP)
|
100% |
15493
1.23 KIPS |
|
Object Detection (Q)
|
91% |
21148
1.69 KIPS |
|
Face Detection (SP)
|
100% |
3613
42.9 IPS |
|
Face Detection (HP)
|
100% |
39552
470.0 IPS |
|
Face Detection (Q)
|
100% |
52847
627.9 IPS |
|
Depth Estimation (SP)
|
100% |
8196
63.1 IPS |
|
Depth Estimation (HP)
|
99% |
94261
726.2 IPS |
|
Depth Estimation (Q)
|
85% |
155022
1.21 KIPS |
|
Style Transfer (SP)
|
100% |
22097
28.4 IPS |
|
Style Transfer (HP)
|
100% |
244518
314.3 IPS |
|
Style Transfer (Q)
|
96% |
293578
378.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5285
195.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
51151
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80049
2.96 KIPS |
|
Text Classification (SP)
|
100% |
3700
4.94 KIPS |
|
Text Classification (HP)
|
99% |
6265
8.36 KIPS |
|
Text Classification (Q)
|
93% |
6116
8.21 KIPS |
|
Machine Translation (SP)
|
100% |
3972
68.4 IPS |
|
Machine Translation (HP)
|
100% |
9017
155.3 IPS |
|
Machine Translation (Q)
|
98% |
10197
176.2 IPS |