| Upload Date | October 25 2025 09:49 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.1 |
| 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
49.3 IPS |
|
|
Image Classification (HP)
|
100% |
2151
400.0 IPS |
|
|
Image Classification (Q)
|
99% |
174
32.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
245
3.97 IPS |
|
|
Image Segmentation (HP)
|
100% |
390
6.33 IPS |
|
|
Image Segmentation (Q)
|
99% |
196
3.18 IPS |
|
|
Pose Estimation (SP)
|
100% |
1146
1.34 IPS |
|
|
Pose Estimation (HP)
|
100% |
24261
28.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
828
0.97 IPS |
|
|
Object Detection (SP)
|
100% |
266
21.1 IPS |
|
|
Object Detection (HP)
|
100% |
1410
111.8 IPS |
|
|
Object Detection (Q)
|
94% |
198
15.8 IPS |
|
|
Face Detection (SP)
|
100% |
649
7.71 IPS |
|
|
Face Detection (HP)
|
100% |
5317
63.2 IPS |
|
|
Face Detection (Q)
|
100% |
251
2.98 IPS |
|
|
Depth Estimation (SP)
|
100% |
502
3.87 IPS |
|
|
Depth Estimation (HP)
|
99% |
17843
137.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
378
2.95 IPS |
|
|
Style Transfer (SP)
|
100% |
1565
2.01 IPS |
|
|
Style Transfer (HP)
|
100% |
1483
1.91 IPS |
|
|
Style Transfer (Q)
|
96% |
1271
1.64 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
500
18.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3506
129.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
455
16.8 IPS |
|
|
Text Classification (SP)
|
100% |
272
362.5 IPS |
|
|
Text Classification (HP)
|
100% |
299
399.3 IPS |
|
|
Text Classification (Q)
|
93% |
300
402.7 IPS |
|
|
Machine Translation (SP)
|
100% |
403
6.95 IPS |
|
|
Machine Translation (HP)
|
100% |
298
5.13 IPS |
|
|
Machine Translation (Q)
|
98% |
282
4.88 IPS |