| Upload Date | December 16 2025 01:45 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| 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% |
669
124.5 IPS |
|
|
Image Classification (HP)
|
100% |
1088
202.4 IPS |
|
|
Image Classification (Q)
|
96% |
787
146.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
750
12.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1115
18.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
1294
21.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
3194
3.73 IPS |
|
|
Pose Estimation (HP)
|
100% |
7377
8.61 IPS |
|
|
Pose Estimation (Q)
|
95% |
6526
7.65 IPS |
|
|
Object Detection (SP)
|
100% |
716
56.8 IPS |
|
|
Object Detection (HP)
|
97% |
1243
98.9 IPS |
|
|
Object Detection (Q)
|
94% |
920
73.3 IPS |
|
|
Face Detection (SP)
|
100% |
1619
19.2 IPS |
|
|
Face Detection (HP)
|
100% |
2983
35.4 IPS |
|
|
Face Detection (Q)
|
100% |
1700
20.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
2661
20.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
5095
39.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
3814
29.8 IPS |
|
|
Style Transfer (SP)
|
100% |
8516
10.9 IPS |
|
|
Style Transfer (HP)
|
100% |
13580
17.5 IPS |
|
|
Style Transfer (Q)
|
96% |
11407
14.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1973
72.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2591
95.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1918
70.8 IPS |
|
|
Text Classification (SP)
|
100% |
1340
1.79 KIPS |
|
|
Text Classification (HP)
|
99% |
2306
3.08 KIPS |
|
|
Text Classification (Q)
|
93% |
2293
3.08 KIPS |
|
|
Machine Translation (SP)
|
100% |
1395
24.0 IPS |
|
|
Machine Translation (HP)
|
98% |
2888
49.9 IPS |
|
|
Machine Translation (Q)
|
98% |
2876
49.7 IPS |