| Upload Date | December 07 2025 05:47 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.2 |
| Model | iPhone XR |
| Model ID | iPhone11,8 |
| Motherboard | N841AP |
| 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 | 2.77 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
369
68.6 IPS |
|
|
Image Classification (HP)
|
100% |
579
107.7 IPS |
|
|
Image Classification (Q)
|
96% |
484
90.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
359
5.82 IPS |
|
|
Image Segmentation (HP)
|
100% |
648
10.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
684
11.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
604
0.71 IPS |
|
|
Pose Estimation (HP)
|
100% |
720
0.84 IPS |
|
|
Pose Estimation (Q)
|
96% |
701
0.82 IPS |
|
|
Object Detection (SP)
|
100% |
267
21.2 IPS |
|
|
Object Detection (HP)
|
99% |
603
47.8 IPS |
|
|
Object Detection (Q)
|
92% |
436
34.8 IPS |
|
|
Face Detection (SP)
|
100% |
712
8.46 IPS |
|
|
Face Detection (HP)
|
100% |
1540
18.3 IPS |
|
|
Face Detection (Q)
|
100% |
984
11.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
647
4.98 IPS |
|
|
Depth Estimation (HP)
|
98% |
1131
8.74 IPS |
|
|
Depth Estimation (Q)
|
85% |
1008
7.88 IPS |
|
|
Style Transfer (SP)
|
100% |
1535
1.97 IPS |
|
|
Style Transfer (HP)
|
100% |
2683
3.45 IPS |
|
|
Style Transfer (Q)
|
96% |
2463
3.18 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
485
17.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
649
24.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
639
23.6 IPS |
|
|
Text Classification (SP)
|
100% |
257
343.5 IPS |
|
|
Text Classification (HP)
|
100% |
541
722.5 IPS |
|
|
Text Classification (Q)
|
93% |
540
725.1 IPS |
|
|
Machine Translation (SP)
|
100% |
459
7.91 IPS |
|
|
Machine Translation (HP)
|
98% |
767
13.3 IPS |
|
|
Machine Translation (Q)
|
98% |
769
13.3 IPS |