| Upload Date | November 20 2025 05:17 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
1576
293.1 IPS |
|
|
Image Classification (HP)
|
100% |
2911
541.4 IPS |
|
|
Image Classification (Q)
|
96% |
2029
378.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1568
25.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
2423
39.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
3040
49.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
7579
8.84 IPS |
|
|
Pose Estimation (HP)
|
100% |
16752
19.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
14569
17.1 IPS |
|
|
Object Detection (SP)
|
100% |
1666
132.2 IPS |
|
|
Object Detection (HP)
|
97% |
3274
260.6 IPS |
|
|
Object Detection (Q)
|
94% |
2361
188.2 IPS |
|
|
Face Detection (SP)
|
100% |
3103
36.9 IPS |
|
|
Face Detection (HP)
|
100% |
6789
80.7 IPS |
|
|
Face Detection (Q)
|
100% |
3855
45.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
6811
52.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
12753
98.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
8940
69.9 IPS |
|
|
Style Transfer (SP)
|
100% |
21039
27.0 IPS |
|
|
Style Transfer (HP)
|
100% |
33676
43.3 IPS |
|
|
Style Transfer (Q)
|
96% |
27735
35.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4679
172.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5663
209.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4337
160.2 IPS |
|
|
Text Classification (SP)
|
100% |
3195
4.26 KIPS |
|
|
Text Classification (HP)
|
99% |
5493
7.33 KIPS |
|
|
Text Classification (Q)
|
93% |
5454
7.32 KIPS |
|
|
Machine Translation (SP)
|
100% |
3179
54.8 IPS |
|
|
Machine Translation (HP)
|
98% |
7426
128.3 IPS |
|
|
Machine Translation (Q)
|
98% |
7480
129.3 IPS |