| User | atti |
| Upload Date | April 04 2026 11:47 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.3.1 |
| 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 | 5.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
405
75.3 IPS |
|
|
Image Classification (HP)
|
100% |
996
185.3 IPS |
|
|
Image Classification (Q)
|
96% |
954
178.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
577
9.35 IPS |
|
|
Image Segmentation (HP)
|
100% |
705
11.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
912
14.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
2544
2.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
5282
6.16 IPS |
|
|
Pose Estimation (Q)
|
95% |
4934
5.78 IPS |
|
|
Object Detection (SP)
|
100% |
757
60.1 IPS |
|
|
Object Detection (HP)
|
97% |
1003
79.9 IPS |
|
|
Object Detection (Q)
|
94% |
627
50.0 IPS |
|
|
Face Detection (SP)
|
100% |
1745
20.7 IPS |
|
|
Face Detection (HP)
|
100% |
2413
28.7 IPS |
|
|
Face Detection (Q)
|
100% |
1111
13.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
2140
16.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
4126
31.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
2690
21.0 IPS |
|
|
Style Transfer (SP)
|
100% |
7797
10.0 IPS |
|
|
Style Transfer (HP)
|
100% |
10319
13.3 IPS |
|
|
Style Transfer (Q)
|
96% |
10392
13.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1278
47.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1703
62.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2191
80.9 IPS |
|
|
Text Classification (SP)
|
100% |
1828
2.44 KIPS |
|
|
Text Classification (HP)
|
99% |
2631
3.51 KIPS |
|
|
Text Classification (Q)
|
93% |
1790
2.40 KIPS |
|
|
Machine Translation (SP)
|
100% |
1440
24.8 IPS |
|
|
Machine Translation (HP)
|
98% |
3463
59.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2075
35.9 IPS |