| Upload Date | November 11 2025 09:59 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 15 Pro |
| Model ID | iPhone16,1 |
| Motherboard | D83AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1905
354.2 IPS |
|
|
Image Classification (HP)
|
100% |
1802
335.1 IPS |
|
|
Image Classification (Q)
|
96% |
2079
388.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
3696
59.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
4234
68.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
4035
65.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
12748
14.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
14938
17.4 IPS |
|
|
Pose Estimation (Q)
|
96% |
14492
17.0 IPS |
|
|
Object Detection (SP)
|
100% |
2663
211.3 IPS |
|
|
Object Detection (HP)
|
100% |
2985
236.8 IPS |
|
|
Object Detection (Q)
|
92% |
2898
231.4 IPS |
|
|
Face Detection (SP)
|
100% |
6557
77.9 IPS |
|
|
Face Detection (HP)
|
100% |
8463
100.6 IPS |
|
|
Face Detection (Q)
|
100% |
7148
84.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
9719
74.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
12294
94.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
11854
92.6 IPS |
|
|
Style Transfer (SP)
|
100% |
25088
32.3 IPS |
|
|
Style Transfer (HP)
|
100% |
22862
29.4 IPS |
|
|
Style Transfer (Q)
|
96% |
28701
37.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6731
248.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6377
235.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6404
236.5 IPS |
|
|
Text Classification (SP)
|
100% |
1926
2.57 KIPS |
|
|
Text Classification (HP)
|
99% |
3985
5.32 KIPS |
|
|
Text Classification (Q)
|
93% |
4070
5.46 KIPS |
|
|
Machine Translation (SP)
|
100% |
1710
29.5 IPS |
|
|
Machine Translation (HP)
|
100% |
1962
33.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1754
30.3 IPS |