| Upload Date | October 29 2025 08:43 AM |
| 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% |
1937
360.3 IPS |
|
|
Image Classification (HP)
|
100% |
3233
601.3 IPS |
|
|
Image Classification (Q)
|
96% |
2118
395.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1638
26.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2515
40.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
2826
45.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
7205
8.41 IPS |
|
|
Pose Estimation (HP)
|
100% |
14861
17.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
12577
14.7 IPS |
|
|
Object Detection (SP)
|
100% |
2084
165.3 IPS |
|
|
Object Detection (HP)
|
97% |
3372
268.5 IPS |
|
|
Object Detection (Q)
|
94% |
2358
187.9 IPS |
|
|
Face Detection (SP)
|
100% |
3247
38.6 IPS |
|
|
Face Detection (HP)
|
100% |
6082
72.3 IPS |
|
|
Face Detection (Q)
|
100% |
3509
41.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
7035
54.2 IPS |
|
|
Depth Estimation (HP)
|
97% |
12116
93.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
8461
66.0 IPS |
|
|
Style Transfer (SP)
|
100% |
18048
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
32618
41.9 IPS |
|
|
Style Transfer (Q)
|
96% |
26508
34.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4721
174.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6817
251.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4553
168.1 IPS |
|
|
Text Classification (SP)
|
100% |
3805
5.08 KIPS |
|
|
Text Classification (HP)
|
99% |
6599
8.81 KIPS |
|
|
Text Classification (Q)
|
93% |
6494
8.72 KIPS |
|
|
Machine Translation (SP)
|
100% |
3660
63.1 IPS |
|
|
Machine Translation (HP)
|
98% |
5515
95.3 IPS |
|
|
Machine Translation (Q)
|
98% |
5658
97.8 IPS |