| Upload Date | November 05 2025 09:29 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 12 |
| Model ID | iPhone13,2 |
| Motherboard | D53gAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.56 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
760
141.4 IPS |
|
|
Image Classification (HP)
|
100% |
4407
819.5 IPS |
|
|
Image Classification (Q)
|
96% |
4480
836.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
572
9.27 IPS |
|
|
Image Segmentation (HP)
|
100% |
3646
59.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
465
7.54 IPS |
|
|
Pose Estimation (SP)
|
100% |
4803
5.60 IPS |
|
|
Pose Estimation (HP)
|
100% |
57588
67.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
59753
70.0 IPS |
|
|
Object Detection (SP)
|
100% |
864
68.5 IPS |
|
|
Object Detection (HP)
|
99% |
5354
425.9 IPS |
|
|
Object Detection (Q)
|
93% |
4828
385.2 IPS |
|
|
Face Detection (SP)
|
100% |
1494
17.7 IPS |
|
|
Face Detection (HP)
|
100% |
11081
131.7 IPS |
|
|
Face Detection (Q)
|
100% |
10602
126.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
3061
23.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
34079
262.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
42435
331.6 IPS |
|
|
Style Transfer (SP)
|
100% |
8946
11.5 IPS |
|
|
Style Transfer (HP)
|
100% |
92994
119.5 IPS |
|
|
Style Transfer (Q)
|
96% |
95955
123.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2250
83.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
13723
506.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
16719
617.3 IPS |
|
|
Text Classification (SP)
|
100% |
899
1.20 KIPS |
|
|
Text Classification (HP)
|
100% |
2877
3.84 KIPS |
|
|
Text Classification (Q)
|
93% |
2732
3.67 KIPS |
|
|
Machine Translation (SP)
|
100% |
1058
18.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1993
34.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1958
33.8 IPS |