| Upload Date | November 13 2025 08:38 AM |
| Views | 3 |
| 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% |
656
122.0 IPS |
|
|
Image Classification (HP)
|
100% |
1060
197.1 IPS |
|
|
Image Classification (Q)
|
96% |
791
147.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
700
11.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
1120
18.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
1296
21.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
3193
3.73 IPS |
|
|
Pose Estimation (HP)
|
100% |
7425
8.66 IPS |
|
|
Pose Estimation (Q)
|
95% |
6463
7.58 IPS |
|
|
Object Detection (SP)
|
100% |
719
57.1 IPS |
|
|
Object Detection (HP)
|
97% |
1250
99.5 IPS |
|
|
Object Detection (Q)
|
94% |
909
72.5 IPS |
|
|
Face Detection (SP)
|
100% |
1638
19.5 IPS |
|
|
Face Detection (HP)
|
100% |
2987
35.5 IPS |
|
|
Face Detection (Q)
|
100% |
1704
20.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
2632
20.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
5180
40.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
3759
29.4 IPS |
|
|
Style Transfer (SP)
|
100% |
8524
11.0 IPS |
|
|
Style Transfer (HP)
|
100% |
13587
17.5 IPS |
|
|
Style Transfer (Q)
|
96% |
11491
14.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1955
72.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2495
92.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1919
70.9 IPS |
|
|
Text Classification (SP)
|
100% |
1372
1.83 KIPS |
|
|
Text Classification (HP)
|
99% |
2369
3.16 KIPS |
|
|
Text Classification (Q)
|
93% |
2352
3.16 KIPS |
|
|
Machine Translation (SP)
|
100% |
1391
24.0 IPS |
|
|
Machine Translation (HP)
|
98% |
2886
49.9 IPS |
|
|
Machine Translation (Q)
|
98% |
2882
49.8 IPS |