| Upload Date | August 11 2025 03:53 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.6 |
| 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% |
566
105.3 IPS |
|
|
Image Classification (HP)
|
100% |
841
156.4 IPS |
|
|
Image Classification (Q)
|
96% |
604
112.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
650
10.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
882
14.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
1021
16.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2696
3.15 IPS |
|
|
Pose Estimation (HP)
|
100% |
6006
7.01 IPS |
|
|
Pose Estimation (Q)
|
95% |
5110
5.99 IPS |
|
|
Object Detection (SP)
|
100% |
589
46.7 IPS |
|
|
Object Detection (HP)
|
97% |
945
75.2 IPS |
|
|
Object Detection (Q)
|
94% |
707
56.3 IPS |
|
|
Face Detection (SP)
|
100% |
1374
16.3 IPS |
|
|
Face Detection (HP)
|
100% |
2255
26.8 IPS |
|
|
Face Detection (Q)
|
100% |
1316
15.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
2223
17.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
4061
31.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
2937
23.0 IPS |
|
|
Style Transfer (SP)
|
100% |
7102
9.13 IPS |
|
|
Style Transfer (HP)
|
100% |
11410
14.7 IPS |
|
|
Style Transfer (Q)
|
96% |
9477
12.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1575
58.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1940
71.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1501
55.4 IPS |
|
|
Text Classification (SP)
|
100% |
1025
1.37 KIPS |
|
|
Text Classification (HP)
|
100% |
1810
2.42 KIPS |
|
|
Text Classification (Q)
|
93% |
1805
2.42 KIPS |
|
|
Machine Translation (SP)
|
100% |
1218
21.0 IPS |
|
|
Machine Translation (HP)
|
98% |
2186
37.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2183
37.7 IPS |