| Upload Date | November 15 2025 07:58 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
759
141.2 IPS |
|
|
Image Classification (HP)
|
100% |
786
146.1 IPS |
|
|
Image Classification (Q)
|
96% |
922
172.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
3584
58.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
4091
66.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
3954
64.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
13066
15.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
14566
17.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
14215
16.6 IPS |
|
|
Object Detection (SP)
|
100% |
1913
151.7 IPS |
|
|
Object Detection (HP)
|
100% |
1630
129.3 IPS |
|
|
Object Detection (Q)
|
92% |
2025
161.6 IPS |
|
|
Face Detection (SP)
|
100% |
7117
84.6 IPS |
|
|
Face Detection (HP)
|
100% |
9282
110.3 IPS |
|
|
Face Detection (Q)
|
100% |
7091
84.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
11245
86.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
12087
93.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
11360
88.7 IPS |
|
|
Style Transfer (SP)
|
100% |
28898
37.1 IPS |
|
|
Style Transfer (HP)
|
100% |
32408
41.7 IPS |
|
|
Style Transfer (Q)
|
96% |
31964
41.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4619
170.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3542
130.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4252
157.0 IPS |
|
|
Text Classification (SP)
|
100% |
3693
4.93 KIPS |
|
|
Text Classification (HP)
|
99% |
6213
8.29 KIPS |
|
|
Text Classification (Q)
|
93% |
6127
8.22 KIPS |
|
|
Machine Translation (SP)
|
100% |
1049
18.1 IPS |
|
|
Machine Translation (HP)
|
100% |
1175
20.2 IPS |
|
|
Machine Translation (Q)
|
98% |
1180
20.4 IPS |