| Upload Date | November 08 2025 04:48 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 16 |
| Model ID | iPhone17,3 |
| Motherboard | D47AP |
| 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 | 7.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2016
375.0 IPS |
|
|
Image Classification (HP)
|
100% |
3261
606.5 IPS |
|
|
Image Classification (Q)
|
96% |
2233
416.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1703
27.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2737
44.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
3162
51.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
8071
9.42 IPS |
|
|
Pose Estimation (HP)
|
100% |
15961
18.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
13305
15.6 IPS |
|
|
Object Detection (SP)
|
100% |
2164
171.6 IPS |
|
|
Object Detection (HP)
|
97% |
3555
283.0 IPS |
|
|
Object Detection (Q)
|
94% |
2477
197.5 IPS |
|
|
Face Detection (SP)
|
100% |
3306
39.3 IPS |
|
|
Face Detection (HP)
|
100% |
6463
76.8 IPS |
|
|
Face Detection (Q)
|
100% |
3639
43.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
7048
54.3 IPS |
|
|
Depth Estimation (HP)
|
97% |
12772
98.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
8735
68.2 IPS |
|
|
Style Transfer (SP)
|
100% |
18357
23.6 IPS |
|
|
Style Transfer (HP)
|
100% |
32686
42.0 IPS |
|
|
Style Transfer (Q)
|
96% |
26475
34.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4779
176.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6460
238.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4600
169.9 IPS |
|
|
Text Classification (SP)
|
100% |
3711
4.95 KIPS |
|
|
Text Classification (HP)
|
99% |
6292
8.40 KIPS |
|
|
Text Classification (Q)
|
93% |
6267
8.41 KIPS |
|
|
Machine Translation (SP)
|
100% |
3800
65.5 IPS |
|
|
Machine Translation (HP)
|
98% |
5364
92.7 IPS |
|
|
Machine Translation (Q)
|
98% |
5765
99.6 IPS |