| Upload Date | February 09 2026 10:03 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.4 |
| 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% |
253
47.1 IPS |
|
|
Image Classification (HP)
|
100% |
2128
395.8 IPS |
|
|
Image Classification (Q)
|
99% |
170
31.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
236
3.83 IPS |
|
|
Image Segmentation (HP)
|
100% |
384
6.23 IPS |
|
|
Image Segmentation (Q)
|
99% |
185
3.00 IPS |
|
|
Pose Estimation (SP)
|
100% |
940
1.10 IPS |
|
|
Pose Estimation (HP)
|
100% |
22931
26.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
791
0.93 IPS |
|
|
Object Detection (SP)
|
100% |
262
20.7 IPS |
|
|
Object Detection (HP)
|
100% |
1412
112.0 IPS |
|
|
Object Detection (Q)
|
94% |
190
15.1 IPS |
|
|
Face Detection (SP)
|
100% |
590
7.02 IPS |
|
|
Face Detection (HP)
|
100% |
5280
62.7 IPS |
|
|
Face Detection (Q)
|
100% |
229
2.73 IPS |
|
|
Depth Estimation (SP)
|
100% |
527
4.06 IPS |
|
|
Depth Estimation (HP)
|
99% |
18482
142.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
358
2.80 IPS |
|
|
Style Transfer (SP)
|
100% |
1332
1.71 IPS |
|
|
Style Transfer (HP)
|
100% |
1380
1.77 IPS |
|
|
Style Transfer (Q)
|
96% |
1255
1.62 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
477
17.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3528
130.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
434
16.0 IPS |
|
|
Text Classification (SP)
|
100% |
270
360.6 IPS |
|
|
Text Classification (HP)
|
100% |
312
417.1 IPS |
|
|
Text Classification (Q)
|
93% |
295
395.9 IPS |
|
|
Machine Translation (SP)
|
100% |
376
6.48 IPS |
|
|
Machine Translation (HP)
|
100% |
286
4.93 IPS |
|
|
Machine Translation (Q)
|
98% |
285
4.92 IPS |