| Upload Date | November 08 2025 12:40 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
1535
285.4 IPS |
|
|
Image Classification (HP)
|
100% |
2921
543.2 IPS |
|
|
Image Classification (Q)
|
96% |
2016
376.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
1523
24.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2329
37.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
3019
48.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
7725
9.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
16815
19.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
14563
17.1 IPS |
|
|
Object Detection (SP)
|
100% |
1659
131.6 IPS |
|
|
Object Detection (HP)
|
97% |
3024
240.7 IPS |
|
|
Object Detection (Q)
|
94% |
2235
178.1 IPS |
|
|
Face Detection (SP)
|
100% |
2749
32.7 IPS |
|
|
Face Detection (HP)
|
100% |
6537
77.7 IPS |
|
|
Face Detection (Q)
|
100% |
3795
45.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
6675
51.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
12595
97.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
8924
69.8 IPS |
|
|
Style Transfer (SP)
|
100% |
20943
26.9 IPS |
|
|
Style Transfer (HP)
|
100% |
33464
43.0 IPS |
|
|
Style Transfer (Q)
|
96% |
27259
35.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4632
171.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5679
209.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4369
161.3 IPS |
|
|
Text Classification (SP)
|
100% |
3289
4.39 KIPS |
|
|
Text Classification (HP)
|
99% |
5593
7.46 KIPS |
|
|
Text Classification (Q)
|
93% |
5409
7.26 KIPS |
|
|
Machine Translation (SP)
|
100% |
2882
49.6 IPS |
|
|
Machine Translation (HP)
|
98% |
6848
118.3 IPS |
|
|
Machine Translation (Q)
|
98% |
6932
119.8 IPS |