| Upload Date | November 08 2025 12:50 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
1855
344.9 IPS |
|
|
Image Classification (HP)
|
100% |
1892
351.9 IPS |
|
|
Image Classification (Q)
|
96% |
2098
391.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
3811
61.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
4271
69.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
4093
66.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
13261
15.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
15247
17.8 IPS |
|
|
Pose Estimation (Q)
|
96% |
14632
17.1 IPS |
|
|
Object Detection (SP)
|
100% |
2336
185.3 IPS |
|
|
Object Detection (HP)
|
100% |
2686
213.1 IPS |
|
|
Object Detection (Q)
|
92% |
2505
199.9 IPS |
|
|
Face Detection (SP)
|
100% |
6409
76.1 IPS |
|
|
Face Detection (HP)
|
100% |
8656
102.9 IPS |
|
|
Face Detection (Q)
|
100% |
6973
82.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
10885
83.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
12434
95.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
11427
89.3 IPS |
|
|
Style Transfer (SP)
|
100% |
26944
34.6 IPS |
|
|
Style Transfer (HP)
|
100% |
32921
42.3 IPS |
|
|
Style Transfer (Q)
|
96% |
33407
43.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5661
209.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5864
216.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5435
200.7 IPS |
|
|
Text Classification (SP)
|
100% |
3252
4.34 KIPS |
|
|
Text Classification (HP)
|
99% |
5496
7.34 KIPS |
|
|
Text Classification (Q)
|
93% |
5441
7.30 KIPS |
|
|
Machine Translation (SP)
|
0% |
0
10.1 IPS |
|
|
Machine Translation (HP)
|
0% |
0
10.8 IPS |
|
|
Machine Translation (Q)
|
0% |
0
9.68 IPS |