| Upload Date | February 14 2026 11:13 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 |
| System Information | |
|---|---|
| Operating System | iOS 26.2.1 |
| Model | iPhone 16 Plus |
| Model ID | iPhone17,4 |
| Motherboard | D48AP |
| CPU Information | |
|---|---|
| Name | Apple A18 |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
524
97.4 IPS |
|
|
Image Classification (HP)
|
100% |
1684
313.1 IPS |
|
|
Image Classification (Q)
|
96% |
636
118.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
953
15.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
736
11.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
877
14.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
2779
3.24 IPS |
|
|
Pose Estimation (HP)
|
100% |
8499
9.92 IPS |
|
|
Pose Estimation (Q)
|
95% |
6911
8.10 IPS |
|
|
Object Detection (SP)
|
100% |
1101
87.4 IPS |
|
|
Object Detection (HP)
|
97% |
1800
143.3 IPS |
|
|
Object Detection (Q)
|
94% |
1467
116.9 IPS |
|
|
Face Detection (SP)
|
100% |
1049
12.5 IPS |
|
|
Face Detection (HP)
|
100% |
3466
41.2 IPS |
|
|
Face Detection (Q)
|
100% |
2130
25.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
3594
27.7 IPS |
|
|
Depth Estimation (HP)
|
97% |
7810
60.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
5523
43.1 IPS |
|
|
Style Transfer (SP)
|
100% |
11607
14.9 IPS |
|
|
Style Transfer (HP)
|
100% |
21593
27.8 IPS |
|
|
Style Transfer (Q)
|
96% |
15461
20.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2237
82.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1806
66.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2808
103.7 IPS |
|
|
Text Classification (SP)
|
100% |
2022
2.70 KIPS |
|
|
Text Classification (HP)
|
99% |
3324
4.44 KIPS |
|
|
Text Classification (Q)
|
93% |
3303
4.43 KIPS |
|
|
Machine Translation (SP)
|
100% |
1756
30.2 IPS |
|
|
Machine Translation (HP)
|
98% |
2489
43.0 IPS |
|
|
Machine Translation (Q)
|
98% |
2550
44.1 IPS |