| Upload Date | June 21 2025 05:39 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.6 |
| 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 | 7.48 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1526
283.9 IPS |
|
|
Image Classification (HP)
|
100% |
2935
545.7 IPS |
|
|
Image Classification (Q)
|
96% |
2006
374.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1514
24.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2342
38.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
2863
46.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
6998
8.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
14494
16.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
12807
15.0 IPS |
|
|
Object Detection (SP)
|
100% |
1639
130.0 IPS |
|
|
Object Detection (HP)
|
97% |
3158
251.4 IPS |
|
|
Object Detection (Q)
|
94% |
2217
176.7 IPS |
|
|
Face Detection (SP)
|
100% |
2750
32.7 IPS |
|
|
Face Detection (HP)
|
100% |
6003
71.3 IPS |
|
|
Face Detection (Q)
|
100% |
3516
41.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
6257
48.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
11889
91.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
8231
64.3 IPS |
|
|
Style Transfer (SP)
|
100% |
18695
24.0 IPS |
|
|
Style Transfer (HP)
|
100% |
30765
39.5 IPS |
|
|
Style Transfer (Q)
|
96% |
25204
32.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4187
154.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5738
211.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4175
154.2 IPS |
|
|
Text Classification (SP)
|
100% |
3203
4.28 KIPS |
|
|
Text Classification (HP)
|
100% |
5759
7.69 KIPS |
|
|
Text Classification (Q)
|
93% |
5683
7.63 KIPS |
|
|
Machine Translation (SP)
|
100% |
2907
50.1 IPS |
|
|
Machine Translation (HP)
|
98% |
6109
105.6 IPS |
|
|
Machine Translation (Q)
|
98% |
6173
106.7 IPS |