| User | OXO |
| Upload Date | September 25 2025 04:28 AM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7 |
| 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% |
216
40.2 IPS |
|
|
Image Classification (HP)
|
100% |
254
47.2 IPS |
|
|
Image Classification (Q)
|
96% |
137
25.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
214
3.46 IPS |
|
|
Image Segmentation (HP)
|
100% |
245
3.97 IPS |
|
|
Image Segmentation (Q)
|
99% |
176
2.86 IPS |
|
|
Pose Estimation (SP)
|
100% |
1644
1.92 IPS |
|
|
Pose Estimation (HP)
|
100% |
1974
2.30 IPS |
|
|
Pose Estimation (Q)
|
96% |
673
0.79 IPS |
|
|
Object Detection (SP)
|
100% |
525
41.6 IPS |
|
|
Object Detection (HP)
|
100% |
550
43.6 IPS |
|
|
Object Detection (Q)
|
92% |
156
12.4 IPS |
|
|
Face Detection (SP)
|
100% |
1906
22.6 IPS |
|
|
Face Detection (HP)
|
100% |
2225
26.4 IPS |
|
|
Face Detection (Q)
|
100% |
262
3.11 IPS |
|
|
Depth Estimation (SP)
|
100% |
1701
13.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
2294
17.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
416
3.25 IPS |
|
|
Style Transfer (SP)
|
100% |
4430
5.69 IPS |
|
|
Style Transfer (HP)
|
100% |
4823
6.20 IPS |
|
|
Style Transfer (Q)
|
96% |
1451
1.87 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
795
29.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1063
39.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
293
10.8 IPS |
|
|
Text Classification (SP)
|
100% |
145
193.0 IPS |
|
|
Text Classification (HP)
|
100% |
198
263.6 IPS |
|
|
Text Classification (Q)
|
93% |
195
262.3 IPS |
|
|
Machine Translation (SP)
|
100% |
192
3.30 IPS |
|
|
Machine Translation (HP)
|
100% |
169
2.91 IPS |
|
|
Machine Translation (Q)
|
98% |
162
2.80 IPS |