| Upload Date | November 09 2025 04:03 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 15 Pro Max |
| Model ID | iPhone16,2 |
| Motherboard | D84AP |
| 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 | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
680
126.5 IPS |
|
|
Image Classification (HP)
|
100% |
1083
201.4 IPS |
|
|
Image Classification (Q)
|
96% |
1080
201.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
557
9.03 IPS |
|
|
Image Segmentation (HP)
|
100% |
561
9.10 IPS |
|
|
Image Segmentation (Q)
|
99% |
873
14.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
1857
2.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
4366
5.09 IPS |
|
|
Pose Estimation (Q)
|
95% |
5877
6.89 IPS |
|
|
Object Detection (SP)
|
100% |
765
60.7 IPS |
|
|
Object Detection (HP)
|
97% |
1025
81.6 IPS |
|
|
Object Detection (Q)
|
94% |
868
69.2 IPS |
|
|
Face Detection (SP)
|
100% |
1240
14.7 IPS |
|
|
Face Detection (HP)
|
100% |
2115
25.1 IPS |
|
|
Face Detection (Q)
|
100% |
1286
15.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
1901
14.6 IPS |
|
|
Depth Estimation (HP)
|
98% |
3941
30.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
2490
19.5 IPS |
|
|
Style Transfer (SP)
|
100% |
5293
6.80 IPS |
|
|
Style Transfer (HP)
|
100% |
10447
13.4 IPS |
|
|
Style Transfer (Q)
|
96% |
7329
9.46 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1679
62.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2475
91.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3023
111.6 IPS |
|
|
Text Classification (SP)
|
100% |
385
514.4 IPS |
|
|
Text Classification (HP)
|
99% |
913
1.22 KIPS |
|
|
Text Classification (Q)
|
93% |
725
973.7 IPS |
|
|
Machine Translation (SP)
|
100% |
695
12.0 IPS |
|
|
Machine Translation (HP)
|
98% |
2285
39.5 IPS |
|
|
Machine Translation (Q)
|
98% |
4544
78.5 IPS |