| Upload Date | November 13 2025 02:43 PM |
| Views | 1 |
| 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% |
2056
382.3 IPS |
|
|
Image Classification (HP)
|
100% |
3286
611.0 IPS |
|
|
Image Classification (Q)
|
96% |
2240
418.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1810
29.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
2772
44.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
3222
52.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
8930
10.4 IPS |
|
|
Pose Estimation (HP)
|
100% |
17579
20.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
14615
17.1 IPS |
|
|
Object Detection (SP)
|
100% |
2277
180.6 IPS |
|
|
Object Detection (HP)
|
97% |
3737
297.5 IPS |
|
|
Object Detection (Q)
|
94% |
2569
204.8 IPS |
|
|
Face Detection (SP)
|
100% |
3556
42.3 IPS |
|
|
Face Detection (HP)
|
100% |
6787
80.6 IPS |
|
|
Face Detection (Q)
|
100% |
3871
46.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
7796
60.1 IPS |
|
|
Depth Estimation (HP)
|
97% |
13168
101.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
9167
71.6 IPS |
|
|
Style Transfer (SP)
|
100% |
19767
25.4 IPS |
|
|
Style Transfer (HP)
|
100% |
34939
44.9 IPS |
|
|
Style Transfer (Q)
|
96% |
28055
36.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5261
194.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7017
259.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5001
184.7 IPS |
|
|
Text Classification (SP)
|
100% |
3692
4.93 KIPS |
|
|
Text Classification (HP)
|
99% |
6284
8.39 KIPS |
|
|
Text Classification (Q)
|
93% |
6243
8.38 KIPS |
|
|
Machine Translation (SP)
|
100% |
3944
67.9 IPS |
|
|
Machine Translation (HP)
|
98% |
6335
109.5 IPS |
|
|
Machine Translation (Q)
|
98% |
6368
110.0 IPS |