| Upload Date | July 02 2025 10:43 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 19.0 |
| Model | iPhone 16 Pro Max |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | Apple A18 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
313
58.2 IPS |
|
|
Image Classification (HP)
|
100% |
926
172.2 IPS |
|
|
Image Classification (Q)
|
96% |
906
169.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
711
11.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1212
19.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1302
21.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
3038
3.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
8058
9.40 IPS |
|
|
Pose Estimation (Q)
|
95% |
6883
8.07 IPS |
|
|
Object Detection (SP)
|
100% |
1010
80.1 IPS |
|
|
Object Detection (HP)
|
97% |
1596
127.1 IPS |
|
|
Object Detection (Q)
|
94% |
1105
88.1 IPS |
|
|
Face Detection (SP)
|
100% |
1524
18.1 IPS |
|
|
Face Detection (HP)
|
100% |
2928
34.8 IPS |
|
|
Face Detection (Q)
|
100% |
1687
20.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
3554
27.4 IPS |
|
|
Depth Estimation (HP)
|
97% |
5840
45.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
4073
31.8 IPS |
|
|
Style Transfer (SP)
|
100% |
9895
12.7 IPS |
|
|
Style Transfer (HP)
|
100% |
15584
20.0 IPS |
|
|
Style Transfer (Q)
|
96% |
12837
16.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2455
90.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3050
112.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2125
78.5 IPS |
|
|
Text Classification (SP)
|
100% |
1472
1.97 KIPS |
|
|
Text Classification (HP)
|
99% |
2631
3.51 KIPS |
|
|
Text Classification (Q)
|
93% |
2489
3.34 KIPS |
|
|
Machine Translation (SP)
|
100% |
1474
25.4 IPS |
|
|
Machine Translation (HP)
|
98% |
2695
46.6 IPS |
|
|
Machine Translation (Q)
|
98% |
2873
49.7 IPS |