| Upload Date | October 20 2025 01:53 AM |
| Views | 8 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 16 Plus |
| Model ID | iPhone17,4 |
| Motherboard | D48AP |
| 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 | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1861
346.1 IPS |
|
|
Image Classification (HP)
|
100% |
2616
486.6 IPS |
|
|
Image Classification (Q)
|
96% |
1888
352.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1546
25.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2429
39.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
2760
44.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
6721
7.84 IPS |
|
|
Pose Estimation (HP)
|
100% |
13708
16.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
11522
13.5 IPS |
|
|
Object Detection (SP)
|
100% |
1922
152.4 IPS |
|
|
Object Detection (HP)
|
97% |
3163
251.8 IPS |
|
|
Object Detection (Q)
|
94% |
2248
179.2 IPS |
|
|
Face Detection (SP)
|
100% |
2637
31.3 IPS |
|
|
Face Detection (HP)
|
100% |
4949
58.8 IPS |
|
|
Face Detection (Q)
|
100% |
3243
38.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
5893
45.4 IPS |
|
|
Depth Estimation (HP)
|
97% |
11136
86.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
7957
62.1 IPS |
|
|
Style Transfer (SP)
|
100% |
15565
20.0 IPS |
|
|
Style Transfer (HP)
|
100% |
29594
38.0 IPS |
|
|
Style Transfer (Q)
|
96% |
24865
32.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4128
152.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6281
231.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3905
144.2 IPS |
|
|
Text Classification (SP)
|
100% |
3633
4.85 KIPS |
|
|
Text Classification (HP)
|
99% |
6113
8.16 KIPS |
|
|
Text Classification (Q)
|
93% |
6034
8.10 KIPS |
|
|
Machine Translation (SP)
|
100% |
3218
55.4 IPS |
|
|
Machine Translation (HP)
|
98% |
4662
80.6 IPS |
|
|
Machine Translation (Q)
|
98% |
4684
80.9 IPS |