| User | brianl831 |
| Upload Date | January 31 2026 11:28 PM |
| Views | 9 |
| 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% |
254
47.3 IPS |
|
|
Image Classification (HP)
|
100% |
298
55.4 IPS |
|
|
Image Classification (Q)
|
96% |
135
25.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
224
3.64 IPS |
|
|
Image Segmentation (HP)
|
100% |
250
4.06 IPS |
|
|
Image Segmentation (Q)
|
99% |
178
2.88 IPS |
|
|
Pose Estimation (SP)
|
100% |
1207
1.41 IPS |
|
|
Pose Estimation (HP)
|
100% |
1404
1.64 IPS |
|
|
Pose Estimation (Q)
|
96% |
662
0.78 IPS |
|
|
Object Detection (SP)
|
100% |
535
42.5 IPS |
|
|
Object Detection (HP)
|
100% |
592
46.9 IPS |
|
|
Object Detection (Q)
|
92% |
158
12.6 IPS |
|
|
Face Detection (SP)
|
100% |
1957
23.3 IPS |
|
|
Face Detection (HP)
|
100% |
2281
27.1 IPS |
|
|
Face Detection (Q)
|
100% |
249
2.96 IPS |
|
|
Depth Estimation (SP)
|
100% |
1750
13.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
2238
17.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
421
3.29 IPS |
|
|
Style Transfer (SP)
|
100% |
4316
5.55 IPS |
|
|
Style Transfer (HP)
|
100% |
4547
5.85 IPS |
|
|
Style Transfer (Q)
|
96% |
1484
1.92 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
817
30.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1074
39.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
296
10.9 IPS |
|
|
Text Classification (SP)
|
100% |
147
196.3 IPS |
|
|
Text Classification (HP)
|
100% |
195
259.8 IPS |
|
|
Text Classification (Q)
|
93% |
200
268.8 IPS |
|
|
Machine Translation (SP)
|
100% |
191
3.30 IPS |
|
|
Machine Translation (HP)
|
100% |
166
2.86 IPS |
|
|
Machine Translation (Q)
|
98% |
171
2.95 IPS |