| Upload Date | December 08 2025 05:51 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A18 |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
831
154.5 IPS |
|
|
Image Classification (HP)
|
100% |
864
160.6 IPS |
|
|
Image Classification (Q)
|
96% |
791
147.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
3922
63.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
4010
65.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
3417
55.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
11793
13.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
14345
16.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
13533
15.9 IPS |
|
|
Object Detection (SP)
|
100% |
1961
155.5 IPS |
|
|
Object Detection (HP)
|
100% |
1510
119.7 IPS |
|
|
Object Detection (Q)
|
92% |
2030
162.0 IPS |
|
|
Face Detection (SP)
|
100% |
7066
84.0 IPS |
|
|
Face Detection (HP)
|
100% |
9276
110.2 IPS |
|
|
Face Detection (Q)
|
100% |
7172
85.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
11270
86.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
12103
93.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
11344
88.6 IPS |
|
|
Style Transfer (SP)
|
100% |
28774
37.0 IPS |
|
|
Style Transfer (HP)
|
100% |
32375
41.6 IPS |
|
|
Style Transfer (Q)
|
96% |
31415
40.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4712
174.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3585
132.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4018
148.3 IPS |
|
|
Text Classification (SP)
|
100% |
3674
4.90 KIPS |
|
|
Text Classification (HP)
|
99% |
6414
8.56 KIPS |
|
|
Text Classification (Q)
|
93% |
6183
8.30 KIPS |
|
|
Machine Translation (SP)
|
100% |
1022
17.6 IPS |
|
|
Machine Translation (HP)
|
100% |
1184
20.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1113
19.2 IPS |