| Upload Date | October 25 2025 06:32 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.0.1 |
| 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% |
1580
293.8 IPS |
|
|
Image Classification (HP)
|
100% |
2964
551.2 IPS |
|
|
Image Classification (Q)
|
96% |
2037
380.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1548
25.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2336
37.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
3023
49.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
7941
9.27 IPS |
|
|
Pose Estimation (HP)
|
100% |
17062
19.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
14683
17.2 IPS |
|
|
Object Detection (SP)
|
100% |
1676
132.9 IPS |
|
|
Object Detection (HP)
|
97% |
3271
260.4 IPS |
|
|
Object Detection (Q)
|
94% |
2360
188.1 IPS |
|
|
Face Detection (SP)
|
100% |
3083
36.6 IPS |
|
|
Face Detection (HP)
|
100% |
6685
79.4 IPS |
|
|
Face Detection (Q)
|
100% |
3828
45.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
6910
53.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
12750
98.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
8953
70.0 IPS |
|
|
Style Transfer (SP)
|
100% |
21390
27.5 IPS |
|
|
Style Transfer (HP)
|
100% |
34008
43.7 IPS |
|
|
Style Transfer (Q)
|
96% |
28137
36.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4700
173.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5719
211.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4350
160.6 IPS |
|
|
Text Classification (SP)
|
100% |
3289
4.39 KIPS |
|
|
Text Classification (HP)
|
99% |
5527
7.38 KIPS |
|
|
Text Classification (Q)
|
93% |
5559
7.46 KIPS |
|
|
Machine Translation (SP)
|
100% |
3138
54.0 IPS |
|
|
Machine Translation (HP)
|
98% |
7310
126.3 IPS |
|
|
Machine Translation (Q)
|
98% |
7365
127.3 IPS |