| Upload Date | October 23 2025 01:25 PM |
| Views | 1 |
| 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% |
778
144.8 IPS |
|
|
Image Classification (HP)
|
100% |
813
151.1 IPS |
|
|
Image Classification (Q)
|
96% |
713
133.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
3856
62.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
3945
64.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
3926
63.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
13030
15.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
14506
16.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
14115
16.5 IPS |
|
|
Object Detection (SP)
|
100% |
2074
164.5 IPS |
|
|
Object Detection (HP)
|
100% |
1532
121.5 IPS |
|
|
Object Detection (Q)
|
92% |
1649
131.6 IPS |
|
|
Face Detection (SP)
|
100% |
6406
76.1 IPS |
|
|
Face Detection (HP)
|
100% |
9235
109.7 IPS |
|
|
Face Detection (Q)
|
100% |
7238
86.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
11133
85.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
11882
91.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
11293
88.2 IPS |
|
|
Style Transfer (SP)
|
100% |
28715
36.9 IPS |
|
|
Style Transfer (HP)
|
100% |
31928
41.0 IPS |
|
|
Style Transfer (Q)
|
96% |
31171
40.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4606
170.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4624
170.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4179
154.3 IPS |
|
|
Text Classification (SP)
|
100% |
3626
4.84 KIPS |
|
|
Text Classification (HP)
|
99% |
6034
8.05 KIPS |
|
|
Text Classification (Q)
|
93% |
6019
8.08 KIPS |
|
|
Machine Translation (SP)
|
0% |
0
8.48 IPS |
|
|
Machine Translation (HP)
|
0% |
0
9.58 IPS |
|
|
Machine Translation (Q)
|
0% |
0
8.51 IPS |