| Upload Date | November 09 2025 02:38 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.48 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
610
113.5 IPS |
|
|
Image Classification (HP)
|
100% |
815
151.6 IPS |
|
|
Image Classification (Q)
|
96% |
601
112.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
542
8.78 IPS |
|
|
Image Segmentation (HP)
|
100% |
532
8.62 IPS |
|
|
Image Segmentation (Q)
|
99% |
772
12.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
2615
3.05 IPS |
|
|
Pose Estimation (HP)
|
100% |
6010
7.01 IPS |
|
|
Pose Estimation (Q)
|
95% |
5323
6.24 IPS |
|
|
Object Detection (SP)
|
100% |
637
50.5 IPS |
|
|
Object Detection (HP)
|
97% |
1012
80.6 IPS |
|
|
Object Detection (Q)
|
94% |
703
56.0 IPS |
|
|
Face Detection (SP)
|
100% |
1334
15.9 IPS |
|
|
Face Detection (HP)
|
100% |
1946
23.1 IPS |
|
|
Face Detection (Q)
|
100% |
1221
14.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
2410
18.6 IPS |
|
|
Depth Estimation (HP)
|
97% |
3799
29.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
2870
22.4 IPS |
|
|
Style Transfer (SP)
|
100% |
7291
9.37 IPS |
|
|
Style Transfer (HP)
|
100% |
11505
14.8 IPS |
|
|
Style Transfer (Q)
|
96% |
9760
12.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1759
65.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2188
80.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1651
61.0 IPS |
|
|
Text Classification (SP)
|
100% |
1198
1.60 KIPS |
|
|
Text Classification (HP)
|
100% |
1955
2.61 KIPS |
|
|
Text Classification (Q)
|
93% |
1956
2.63 KIPS |
|
|
Machine Translation (SP)
|
100% |
1338
23.0 IPS |
|
|
Machine Translation (HP)
|
98% |
2098
36.2 IPS |
|
|
Machine Translation (Q)
|
98% |
2088
36.1 IPS |