Upload Date | August 09 2025 04:48 PM |
Views | 5 |
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% |
1994
370.8 IPS |
|
Image Classification (HP)
|
100% |
14155
2.63 KIPS |
|
Image Classification (Q)
|
97% |
18300
3.42 KIPS |
|
Image Segmentation (SP)
|
100% |
1758
28.5 IPS |
|
Image Segmentation (HP)
|
100% |
18119
293.7 IPS |
|
Image Segmentation (Q)
|
99% |
23390
379.2 IPS |
|
Pose Estimation (SP)
|
100% |
8740
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
147569
172.2 IPS |
|
Pose Estimation (Q)
|
95% |
287681
337.2 IPS |
|
Object Detection (SP)
|
100% |
2325
184.5 IPS |
|
Object Detection (HP)
|
100% |
15862
1.26 KIPS |
|
Object Detection (Q)
|
91% |
21554
1.72 KIPS |
|
Face Detection (SP)
|
100% |
3532
42.0 IPS |
|
Face Detection (HP)
|
100% |
39462
468.9 IPS |
|
Face Detection (Q)
|
100% |
53212
632.3 IPS |
|
Depth Estimation (SP)
|
100% |
7841
60.4 IPS |
|
Depth Estimation (HP)
|
99% |
93781
722.5 IPS |
|
Depth Estimation (Q)
|
85% |
152683
1.19 KIPS |
|
Style Transfer (SP)
|
100% |
20952
26.9 IPS |
|
Style Transfer (HP)
|
100% |
244057
313.7 IPS |
|
Style Transfer (Q)
|
96% |
293771
379.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5094
188.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
50818
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76249
2.82 KIPS |
|
Text Classification (SP)
|
100% |
3673
4.90 KIPS |
|
Text Classification (HP)
|
99% |
6132
8.18 KIPS |
|
Text Classification (Q)
|
93% |
6167
8.28 KIPS |
|
Machine Translation (SP)
|
100% |
3868
66.6 IPS |
|
Machine Translation (HP)
|
100% |
10883
187.5 IPS |
|
Machine Translation (Q)
|
98% |
12427
214.8 IPS |