| Upload Date | November 18 2025 10:54 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 13 mini |
| Model ID | iPhone14,4 |
| Motherboard | D16AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.23 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.59 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
888
165.2 IPS |
|
|
Image Classification (HP)
|
100% |
1041
193.6 IPS |
|
|
Image Classification (Q)
|
96% |
679
126.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
2399
38.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
2431
39.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
2289
37.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
9348
10.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
10512
12.3 IPS |
|
|
Pose Estimation (Q)
|
96% |
10198
11.9 IPS |
|
|
Object Detection (SP)
|
100% |
990
78.5 IPS |
|
|
Object Detection (HP)
|
100% |
1067
84.7 IPS |
|
|
Object Detection (Q)
|
92% |
770
61.4 IPS |
|
|
Face Detection (SP)
|
100% |
4441
52.8 IPS |
|
|
Face Detection (HP)
|
100% |
5234
62.2 IPS |
|
|
Face Detection (Q)
|
100% |
3893
46.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7785
60.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
8381
64.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
7005
54.7 IPS |
|
|
Style Transfer (SP)
|
100% |
16843
21.7 IPS |
|
|
Style Transfer (HP)
|
100% |
19988
25.7 IPS |
|
|
Style Transfer (Q)
|
96% |
19424
25.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2979
110.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3059
113.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2682
99.0 IPS |
|
|
Text Classification (SP)
|
100% |
2540
3.39 KIPS |
|
|
Text Classification (HP)
|
99% |
4197
5.60 KIPS |
|
|
Text Classification (Q)
|
93% |
4167
5.59 KIPS |
|
|
Machine Translation (SP)
|
100% |
850
14.6 IPS |
|
|
Machine Translation (HP)
|
100% |
903
15.6 IPS |
|
|
Machine Translation (Q)
|
98% |
833
14.4 IPS |