| Upload Date | November 11 2025 08:11 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 12 Mini |
| Model ID | iPhone13,1 |
| Motherboard | D52gAP |
| 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 | 3.61 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1227
228.2 IPS |
|
|
Image Classification (HP)
|
100% |
2028
377.2 IPS |
|
|
Image Classification (Q)
|
96% |
1458
272.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1124
18.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1742
28.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
2204
35.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
5070
5.92 IPS |
|
|
Pose Estimation (HP)
|
100% |
10741
12.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
9442
11.1 IPS |
|
|
Object Detection (SP)
|
100% |
1216
96.4 IPS |
|
|
Object Detection (HP)
|
97% |
2248
179.0 IPS |
|
|
Object Detection (Q)
|
94% |
1660
132.3 IPS |
|
|
Face Detection (SP)
|
100% |
2535
30.1 IPS |
|
|
Face Detection (HP)
|
100% |
4725
56.1 IPS |
|
|
Face Detection (Q)
|
100% |
2698
32.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4737
36.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
9142
70.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
6688
52.3 IPS |
|
|
Style Transfer (SP)
|
100% |
12809
16.5 IPS |
|
|
Style Transfer (HP)
|
100% |
22009
28.3 IPS |
|
|
Style Transfer (Q)
|
96% |
19160
24.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2650
97.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4093
151.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3228
119.2 IPS |
|
|
Text Classification (SP)
|
100% |
2307
3.08 KIPS |
|
|
Text Classification (HP)
|
99% |
3905
5.21 KIPS |
|
|
Text Classification (Q)
|
93% |
3877
5.20 KIPS |
|
|
Machine Translation (SP)
|
100% |
2264
39.0 IPS |
|
|
Machine Translation (HP)
|
98% |
4236
73.2 IPS |
|
|
Machine Translation (Q)
|
98% |
4244
73.3 IPS |