| Upload Date | December 16 2025 08:04 PM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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 | 3.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1229
228.5 IPS |
|
|
Image Classification (HP)
|
100% |
2021
375.8 IPS |
|
|
Image Classification (Q)
|
96% |
1451
271.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1112
18.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1727
28.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
2171
35.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
4903
5.72 IPS |
|
|
Pose Estimation (HP)
|
100% |
10717
12.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
9406
11.0 IPS |
|
|
Object Detection (SP)
|
100% |
1184
93.9 IPS |
|
|
Object Detection (HP)
|
97% |
2229
177.4 IPS |
|
|
Object Detection (Q)
|
94% |
1625
129.5 IPS |
|
|
Face Detection (SP)
|
100% |
2496
29.7 IPS |
|
|
Face Detection (HP)
|
100% |
4650
55.3 IPS |
|
|
Face Detection (Q)
|
100% |
2636
31.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
4600
35.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
9186
71.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
6523
51.0 IPS |
|
|
Style Transfer (SP)
|
100% |
12757
16.4 IPS |
|
|
Style Transfer (HP)
|
100% |
21559
27.7 IPS |
|
|
Style Transfer (Q)
|
96% |
18610
24.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2650
97.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4042
149.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3172
117.1 IPS |
|
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
|
Text Classification (HP)
|
99% |
3927
5.24 KIPS |
|
|
Text Classification (Q)
|
93% |
3902
5.24 KIPS |
|
|
Machine Translation (SP)
|
100% |
2240
38.6 IPS |
|
|
Machine Translation (HP)
|
98% |
4240
73.3 IPS |
|
|
Machine Translation (Q)
|
98% |
4245
73.4 IPS |