| User | iantm |
| Upload Date | February 01 2026 04:49 PM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.3 |
| 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% |
243
45.2 IPS |
|
|
Image Classification (HP)
|
100% |
606
112.8 IPS |
|
|
Image Classification (Q)
|
96% |
511
95.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
338
5.49 IPS |
|
|
Image Segmentation (HP)
|
100% |
578
9.37 IPS |
|
|
Image Segmentation (Q)
|
99% |
577
9.38 IPS |
|
|
Pose Estimation (SP)
|
100% |
695
0.81 IPS |
|
|
Pose Estimation (HP)
|
100% |
748
0.87 IPS |
|
|
Pose Estimation (Q)
|
96% |
767
0.90 IPS |
|
|
Object Detection (SP)
|
100% |
290
23.0 IPS |
|
|
Object Detection (HP)
|
99% |
638
50.6 IPS |
|
|
Object Detection (Q)
|
92% |
509
40.6 IPS |
|
|
Face Detection (SP)
|
100% |
780
9.27 IPS |
|
|
Face Detection (HP)
|
100% |
1696
20.1 IPS |
|
|
Face Detection (Q)
|
100% |
1066
12.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
651
5.01 IPS |
|
|
Depth Estimation (HP)
|
98% |
1251
9.67 IPS |
|
|
Depth Estimation (Q)
|
85% |
1101
8.60 IPS |
|
|
Style Transfer (SP)
|
100% |
1519
1.95 IPS |
|
|
Style Transfer (HP)
|
100% |
2644
3.40 IPS |
|
|
Style Transfer (Q)
|
96% |
2613
3.37 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
503
18.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
745
27.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
640
23.6 IPS |
|
|
Text Classification (SP)
|
100% |
284
378.4 IPS |
|
|
Text Classification (HP)
|
100% |
556
741.9 IPS |
|
|
Text Classification (Q)
|
93% |
552
740.6 IPS |
|
|
Machine Translation (SP)
|
100% |
486
8.37 IPS |
|
|
Machine Translation (HP)
|
98% |
898
15.5 IPS |
|
|
Machine Translation (Q)
|
98% |
879
15.2 IPS |