| Upload Date | November 21 2026 06:44 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 27.3 |
| 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 | 7.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1234
229.6 IPS |
|
|
Image Classification (HP)
|
100% |
2185
406.4 IPS |
|
|
Image Classification (Q)
|
96% |
1489
278.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1325
21.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1984
32.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
2360
38.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
5699
6.65 IPS |
|
|
Pose Estimation (HP)
|
100% |
13042
15.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
11079
13.0 IPS |
|
|
Object Detection (SP)
|
100% |
1370
108.7 IPS |
|
|
Object Detection (HP)
|
97% |
2546
202.7 IPS |
|
|
Object Detection (Q)
|
94% |
1774
141.4 IPS |
|
|
Face Detection (SP)
|
100% |
2470
29.4 IPS |
|
|
Face Detection (HP)
|
100% |
5237
62.2 IPS |
|
|
Face Detection (Q)
|
100% |
2849
33.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
5275
40.6 IPS |
|
|
Depth Estimation (HP)
|
98% |
10218
79.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
7032
55.0 IPS |
|
|
Style Transfer (SP)
|
100% |
16046
20.6 IPS |
|
|
Style Transfer (HP)
|
100% |
25876
33.3 IPS |
|
|
Style Transfer (Q)
|
96% |
21104
27.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3366
124.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4380
161.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3249
120.0 IPS |
|
|
Text Classification (SP)
|
100% |
4475
5.97 KIPS |
|
|
Text Classification (HP)
|
99% |
7412
9.89 KIPS |
|
|
Text Classification (Q)
|
93% |
7435
9.98 KIPS |
|
|
Machine Translation (SP)
|
100% |
2278
39.2 IPS |
|
|
Machine Translation (HP)
|
98% |
5809
100.4 IPS |
|
|
Machine Translation (Q)
|
98% |
5694
98.4 IPS |