| Upload Date | November 19 2025 10:08 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
345
64.2 IPS |
|
|
Image Classification (HP)
|
100% |
335
62.3 IPS |
|
|
Image Classification (Q)
|
96% |
310
58.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1394
22.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
1705
27.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
1711
27.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
4213
4.92 IPS |
|
|
Pose Estimation (HP)
|
100% |
6890
8.04 IPS |
|
|
Pose Estimation (Q)
|
94% |
5716
6.70 IPS |
|
|
Object Detection (SP)
|
100% |
679
53.9 IPS |
|
|
Object Detection (HP)
|
100% |
639
50.7 IPS |
|
|
Object Detection (Q)
|
92% |
620
49.5 IPS |
|
|
Face Detection (SP)
|
100% |
2870
34.1 IPS |
|
|
Face Detection (HP)
|
100% |
3446
41.0 IPS |
|
|
Face Detection (Q)
|
100% |
2700
32.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4393
33.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
5533
42.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
4082
31.9 IPS |
|
|
Style Transfer (SP)
|
100% |
11266
14.5 IPS |
|
|
Style Transfer (HP)
|
100% |
13679
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
13390
17.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1588
58.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1544
57.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1427
52.7 IPS |
|
|
Text Classification (SP)
|
100% |
1370
1.83 KIPS |
|
|
Text Classification (HP)
|
99% |
2323
3.10 KIPS |
|
|
Text Classification (Q)
|
93% |
2314
3.11 KIPS |
|
|
Machine Translation (SP)
|
100% |
487
8.38 IPS |
|
|
Machine Translation (HP)
|
100% |
498
8.58 IPS |
|
|
Machine Translation (Q)
|
98% |
500
8.64 IPS |