| Upload Date | October 21 2025 08:25 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.1 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
300
55.9 IPS |
|
|
Image Classification (HP)
|
100% |
600
111.5 IPS |
|
|
Image Classification (Q)
|
96% |
497
92.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
380
6.16 IPS |
|
|
Image Segmentation (HP)
|
100% |
691
11.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
730
11.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
733
0.86 IPS |
|
|
Pose Estimation (HP)
|
100% |
785
0.92 IPS |
|
|
Pose Estimation (Q)
|
96% |
762
0.89 IPS |
|
|
Object Detection (SP)
|
100% |
286
22.7 IPS |
|
|
Object Detection (HP)
|
99% |
652
51.7 IPS |
|
|
Object Detection (Q)
|
92% |
514
41.0 IPS |
|
|
Face Detection (SP)
|
100% |
805
9.56 IPS |
|
|
Face Detection (HP)
|
100% |
1729
20.5 IPS |
|
|
Face Detection (Q)
|
100% |
1093
13.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
740
5.70 IPS |
|
|
Depth Estimation (HP)
|
98% |
1373
10.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
1163
9.09 IPS |
|
|
Style Transfer (SP)
|
100% |
1725
2.22 IPS |
|
|
Style Transfer (HP)
|
100% |
2952
3.79 IPS |
|
|
Style Transfer (Q)
|
96% |
2754
3.55 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
529
19.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
761
28.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
630
23.3 IPS |
|
|
Text Classification (SP)
|
100% |
281
375.0 IPS |
|
|
Text Classification (HP)
|
100% |
564
752.7 IPS |
|
|
Text Classification (Q)
|
93% |
563
755.2 IPS |
|
|
Machine Translation (SP)
|
100% |
486
8.37 IPS |
|
|
Machine Translation (HP)
|
98% |
922
15.9 IPS |
|
|
Machine Translation (Q)
|
98% |
917
15.8 IPS |