| Upload Date | December 02 2025 08:30 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.2 |
| 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% |
265
49.2 IPS |
|
|
Image Classification (HP)
|
100% |
2008
373.4 IPS |
|
|
Image Classification (Q)
|
99% |
170
31.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
237
3.85 IPS |
|
|
Image Segmentation (HP)
|
100% |
382
6.19 IPS |
|
|
Image Segmentation (Q)
|
99% |
189
3.06 IPS |
|
|
Pose Estimation (SP)
|
100% |
936
1.09 IPS |
|
|
Pose Estimation (HP)
|
100% |
20983
24.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
705
0.83 IPS |
|
|
Object Detection (SP)
|
100% |
234
18.5 IPS |
|
|
Object Detection (HP)
|
100% |
1414
112.2 IPS |
|
|
Object Detection (Q)
|
94% |
178
14.2 IPS |
|
|
Face Detection (SP)
|
100% |
576
6.84 IPS |
|
|
Face Detection (HP)
|
100% |
5264
62.6 IPS |
|
|
Face Detection (Q)
|
100% |
219
2.60 IPS |
|
|
Depth Estimation (SP)
|
100% |
557
4.29 IPS |
|
|
Depth Estimation (HP)
|
99% |
18509
142.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
361
2.82 IPS |
|
|
Style Transfer (SP)
|
100% |
1492
1.92 IPS |
|
|
Style Transfer (HP)
|
100% |
1485
1.91 IPS |
|
|
Style Transfer (Q)
|
96% |
1233
1.59 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
461
17.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3500
129.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
435
16.1 IPS |
|
|
Text Classification (SP)
|
100% |
265
354.3 IPS |
|
|
Text Classification (HP)
|
100% |
291
387.9 IPS |
|
|
Text Classification (Q)
|
93% |
296
397.4 IPS |
|
|
Machine Translation (SP)
|
100% |
382
6.58 IPS |
|
|
Machine Translation (HP)
|
100% |
285
4.91 IPS |
|
|
Machine Translation (Q)
|
98% |
283
4.89 IPS |