| Upload Date | August 15 2025 10:11 PM |
| Views | 18 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.6.1 |
| 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 | 7.48 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1677
311.8 IPS |
|
|
Image Classification (HP)
|
100% |
2938
546.3 IPS |
|
|
Image Classification (Q)
|
96% |
2046
382.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1585
25.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2370
38.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
3020
49.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
7693
8.98 IPS |
|
|
Pose Estimation (HP)
|
100% |
15615
18.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
13601
15.9 IPS |
|
|
Object Detection (SP)
|
100% |
1710
135.6 IPS |
|
|
Object Detection (HP)
|
97% |
3264
259.9 IPS |
|
|
Object Detection (Q)
|
94% |
2301
183.4 IPS |
|
|
Face Detection (SP)
|
100% |
2994
35.6 IPS |
|
|
Face Detection (HP)
|
100% |
6498
77.2 IPS |
|
|
Face Detection (Q)
|
100% |
3634
43.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
6583
50.7 IPS |
|
|
Depth Estimation (HP)
|
98% |
12533
96.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
8672
67.8 IPS |
|
|
Style Transfer (SP)
|
100% |
19743
25.4 IPS |
|
|
Style Transfer (HP)
|
100% |
32628
41.9 IPS |
|
|
Style Transfer (Q)
|
96% |
26575
34.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4458
164.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5905
218.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4369
161.3 IPS |
|
|
Text Classification (SP)
|
100% |
3313
4.42 KIPS |
|
|
Text Classification (HP)
|
100% |
5933
7.92 KIPS |
|
|
Text Classification (Q)
|
93% |
5864
7.87 KIPS |
|
|
Machine Translation (SP)
|
100% |
3072
52.9 IPS |
|
|
Machine Translation (HP)
|
98% |
6716
116.1 IPS |
|
|
Machine Translation (Q)
|
98% |
6691
115.6 IPS |