| User | igniz1215 |
| Upload Date | October 08 2025 07:05 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.1 |
| Model | iPhone XS Max |
| Model ID | iPhone11,6 |
| Motherboard | D331pAP |
| 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 | 3.67 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
382
71.0 IPS |
|
|
Image Classification (HP)
|
100% |
662
123.2 IPS |
|
|
Image Classification (Q)
|
96% |
546
102.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
418
6.78 IPS |
|
|
Image Segmentation (HP)
|
100% |
735
11.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
782
12.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
1183
1.38 IPS |
|
|
Pose Estimation (HP)
|
100% |
1062
1.24 IPS |
|
|
Pose Estimation (Q)
|
96% |
867
1.02 IPS |
|
|
Object Detection (SP)
|
100% |
320
25.3 IPS |
|
|
Object Detection (HP)
|
99% |
668
53.0 IPS |
|
|
Object Detection (Q)
|
92% |
560
44.7 IPS |
|
|
Face Detection (SP)
|
100% |
839
9.97 IPS |
|
|
Face Detection (HP)
|
100% |
1791
21.3 IPS |
|
|
Face Detection (Q)
|
100% |
1140
13.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
751
5.79 IPS |
|
|
Depth Estimation (HP)
|
98% |
1376
10.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
1241
9.70 IPS |
|
|
Style Transfer (SP)
|
100% |
1839
2.36 IPS |
|
|
Style Transfer (HP)
|
100% |
3231
4.15 IPS |
|
|
Style Transfer (Q)
|
96% |
3026
3.90 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
575
21.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
856
31.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
713
26.3 IPS |
|
|
Text Classification (SP)
|
100% |
285
380.8 IPS |
|
|
Text Classification (HP)
|
100% |
565
753.7 IPS |
|
|
Text Classification (Q)
|
93% |
563
756.0 IPS |
|
|
Machine Translation (SP)
|
100% |
518
8.92 IPS |
|
|
Machine Translation (HP)
|
98% |
988
17.1 IPS |
|
|
Machine Translation (Q)
|
98% |
941
16.3 IPS |