| Upload Date | November 21 2026 09:51 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 27.2 |
| Model | iPhone 15 Pro |
| Model ID | iPhone16,1 |
| Motherboard | D83AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1640
305.0 IPS |
|
|
Image Classification (HP)
|
100% |
2909
541.1 IPS |
|
|
Image Classification (Q)
|
96% |
1963
366.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1672
27.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2460
39.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
3097
50.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
7386
8.62 IPS |
|
|
Pose Estimation (HP)
|
100% |
17276
20.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
14643
17.2 IPS |
|
|
Object Detection (SP)
|
100% |
1776
140.9 IPS |
|
|
Object Detection (HP)
|
97% |
3305
263.1 IPS |
|
|
Object Detection (Q)
|
94% |
2329
185.6 IPS |
|
|
Face Detection (SP)
|
100% |
3368
40.0 IPS |
|
|
Face Detection (HP)
|
100% |
7020
83.4 IPS |
|
|
Face Detection (Q)
|
100% |
3882
46.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
6917
53.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
13398
103.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
9207
72.0 IPS |
|
|
Style Transfer (SP)
|
100% |
21107
27.1 IPS |
|
|
Style Transfer (HP)
|
100% |
34218
44.0 IPS |
|
|
Style Transfer (Q)
|
96% |
28041
36.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4257
157.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5684
209.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4312
159.2 IPS |
|
|
Text Classification (SP)
|
100% |
5668
7.57 KIPS |
|
|
Text Classification (HP)
|
99% |
8912
11.9 KIPS |
|
|
Text Classification (Q)
|
93% |
8690
11.7 KIPS |
|
|
Machine Translation (SP)
|
100% |
3244
55.9 IPS |
|
|
Machine Translation (HP)
|
98% |
6713
116.0 IPS |
|
|
Machine Translation (Q)
|
98% |
6617
114.3 IPS |