| User | bgh0809 |
| Upload Date | November 19 2025 10:05 PM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.2 |
| Model | iPhone XR |
| Model ID | iPhone11,8 |
| Motherboard | N841AP |
| 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 | 2.77 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
249
46.2 IPS |
|
|
Image Classification (HP)
|
100% |
256
47.6 IPS |
|
|
Image Classification (Q)
|
96% |
113
21.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
220
3.56 IPS |
|
|
Image Segmentation (HP)
|
100% |
251
4.07 IPS |
|
|
Image Segmentation (Q)
|
99% |
181
2.93 IPS |
|
|
Pose Estimation (SP)
|
100% |
1002
1.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
1301
1.52 IPS |
|
|
Pose Estimation (Q)
|
96% |
679
0.80 IPS |
|
|
Object Detection (SP)
|
100% |
499
39.6 IPS |
|
|
Object Detection (HP)
|
100% |
572
45.4 IPS |
|
|
Object Detection (Q)
|
92% |
132
10.5 IPS |
|
|
Face Detection (SP)
|
100% |
1867
22.2 IPS |
|
|
Face Detection (HP)
|
100% |
2000
23.8 IPS |
|
|
Face Detection (Q)
|
100% |
205
2.43 IPS |
|
|
Depth Estimation (SP)
|
100% |
1631
12.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
1559
12.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
405
3.16 IPS |
|
|
Style Transfer (SP)
|
100% |
3940
5.06 IPS |
|
|
Style Transfer (HP)
|
100% |
2847
3.66 IPS |
|
|
Style Transfer (Q)
|
96% |
1565
2.02 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
759
28.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
777
28.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
237
8.77 IPS |
|
|
Text Classification (SP)
|
100% |
148
197.4 IPS |
|
|
Text Classification (HP)
|
100% |
220
293.4 IPS |
|
|
Text Classification (Q)
|
93% |
209
280.7 IPS |
|
|
Machine Translation (SP)
|
100% |
194
3.33 IPS |
|
|
Machine Translation (HP)
|
100% |
167
2.87 IPS |
|
|
Machine Translation (Q)
|
98% |
168
2.91 IPS |