| Upload Date | November 16 2025 02:41 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 15 Pro |
| Model ID | iPhone16,1 |
| Motherboard | D83AP |
| 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% |
785
145.9 IPS |
|
|
Image Classification (HP)
|
100% |
894
166.3 IPS |
|
|
Image Classification (Q)
|
96% |
677
126.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
618
10.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
593
9.61 IPS |
|
|
Image Segmentation (Q)
|
99% |
868
14.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
3635
4.24 IPS |
|
|
Pose Estimation (HP)
|
100% |
7068
8.25 IPS |
|
|
Pose Estimation (Q)
|
95% |
6255
7.33 IPS |
|
|
Object Detection (SP)
|
100% |
748
59.4 IPS |
|
|
Object Detection (HP)
|
97% |
1156
92.1 IPS |
|
|
Object Detection (Q)
|
94% |
855
68.2 IPS |
|
|
Face Detection (SP)
|
100% |
1469
17.5 IPS |
|
|
Face Detection (HP)
|
100% |
2296
27.3 IPS |
|
|
Face Detection (Q)
|
100% |
1366
16.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
2839
21.9 IPS |
|
|
Depth Estimation (HP)
|
97% |
4332
33.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
3271
25.5 IPS |
|
|
Style Transfer (SP)
|
100% |
8701
11.2 IPS |
|
|
Style Transfer (HP)
|
100% |
13099
16.8 IPS |
|
|
Style Transfer (Q)
|
96% |
11279
14.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2197
81.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2604
96.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1866
68.9 IPS |
|
|
Text Classification (SP)
|
100% |
1368
1.83 KIPS |
|
|
Text Classification (HP)
|
100% |
2262
3.02 KIPS |
|
|
Text Classification (Q)
|
93% |
2239
3.01 KIPS |
|
|
Machine Translation (SP)
|
100% |
1299
22.4 IPS |
|
|
Machine Translation (HP)
|
98% |
2261
39.1 IPS |
|
|
Machine Translation (Q)
|
98% |
2225
38.5 IPS |