| Upload Date | November 25 2025 06:10 AM |
| Views | 1 |
| 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% |
1217
226.3 IPS |
|
|
Image Classification (HP)
|
100% |
2028
377.1 IPS |
|
|
Image Classification (Q)
|
96% |
1456
272.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1108
18.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1704
27.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
2120
34.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
4320
5.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
9278
10.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
8147
9.55 IPS |
|
|
Object Detection (SP)
|
100% |
1161
92.1 IPS |
|
|
Object Detection (HP)
|
97% |
2144
170.7 IPS |
|
|
Object Detection (Q)
|
94% |
1573
125.4 IPS |
|
|
Face Detection (SP)
|
100% |
2380
28.3 IPS |
|
|
Face Detection (HP)
|
100% |
4360
51.8 IPS |
|
|
Face Detection (Q)
|
100% |
2464
29.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
4126
31.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
8148
63.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
6074
47.5 IPS |
|
|
Style Transfer (SP)
|
100% |
11171
14.4 IPS |
|
|
Style Transfer (HP)
|
100% |
19425
25.0 IPS |
|
|
Style Transfer (Q)
|
96% |
16890
21.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2299
84.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3809
140.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3051
112.7 IPS |
|
|
Text Classification (SP)
|
100% |
2300
3.07 KIPS |
|
|
Text Classification (HP)
|
99% |
3899
5.20 KIPS |
|
|
Text Classification (Q)
|
93% |
3877
5.20 KIPS |
|
|
Machine Translation (SP)
|
100% |
2155
37.1 IPS |
|
|
Machine Translation (HP)
|
98% |
4142
71.6 IPS |
|
|
Machine Translation (Q)
|
98% |
4152
71.8 IPS |