| Upload Date | December 17 2025 09:24 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
350
65.1 IPS |
|
|
Image Classification (HP)
|
100% |
346
64.3 IPS |
|
|
Image Classification (Q)
|
96% |
307
57.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1401
22.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
1722
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1685
27.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
4218
4.92 IPS |
|
|
Pose Estimation (HP)
|
100% |
6901
8.05 IPS |
|
|
Pose Estimation (Q)
|
94% |
5811
6.81 IPS |
|
|
Object Detection (SP)
|
100% |
673
53.4 IPS |
|
|
Object Detection (HP)
|
100% |
613
48.6 IPS |
|
|
Object Detection (Q)
|
92% |
667
53.2 IPS |
|
|
Face Detection (SP)
|
100% |
2859
34.0 IPS |
|
|
Face Detection (HP)
|
100% |
3558
42.3 IPS |
|
|
Face Detection (Q)
|
100% |
3118
37.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
4211
32.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
5637
43.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
4100
32.0 IPS |
|
|
Style Transfer (SP)
|
100% |
11266
14.5 IPS |
|
|
Style Transfer (HP)
|
100% |
13649
17.5 IPS |
|
|
Style Transfer (Q)
|
96% |
13336
17.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1667
61.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1605
59.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1356
50.1 IPS |
|
|
Text Classification (SP)
|
100% |
1368
1.83 KIPS |
|
|
Text Classification (HP)
|
99% |
2357
3.15 KIPS |
|
|
Text Classification (Q)
|
93% |
2341
3.14 KIPS |
|
|
Machine Translation (SP)
|
100% |
488
8.41 IPS |
|
|
Machine Translation (HP)
|
100% |
499
8.59 IPS |
|
|
Machine Translation (Q)
|
98% |
495
8.55 IPS |