Upload Date | September 19 2025 07:52 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0 |
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% |
1342
249.6 IPS |
|
Image Classification (HP)
|
100% |
9368
1.74 KIPS |
|
Image Classification (Q)
|
97% |
11705
2.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1380
22.4 IPS |
|
Image Segmentation (HP)
|
100% |
15811
256.3 IPS |
|
Image Segmentation (Q)
|
99% |
19033
308.5 IPS |
|
Pose Estimation (SP)
|
100% |
6508
7.59 IPS |
|
Pose Estimation (HP)
|
100% |
98513
114.9 IPS |
|
Pose Estimation (Q)
|
95% |
102372
120.0 IPS |
|
Object Detection (SP)
|
100% |
1471
116.7 IPS |
|
Object Detection (HP)
|
100% |
11698
927.9 IPS |
|
Object Detection (Q)
|
91% |
14731
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3127
37.1 IPS |
|
Face Detection (HP)
|
100% |
27018
321.0 IPS |
|
Face Detection (Q)
|
100% |
38824
461.3 IPS |
|
Depth Estimation (SP)
|
100% |
5932
45.7 IPS |
|
Depth Estimation (HP)
|
99% |
71825
553.4 IPS |
|
Depth Estimation (Q)
|
85% |
91339
714.1 IPS |
|
Style Transfer (SP)
|
100% |
18642
24.0 IPS |
|
Style Transfer (HP)
|
100% |
171041
219.9 IPS |
|
Style Transfer (Q)
|
96% |
171098
220.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3893
143.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
31960
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35325
1.30 KIPS |
|
Text Classification (SP)
|
100% |
2828
3.78 KIPS |
|
Text Classification (HP)
|
100% |
2560
3.42 KIPS |
|
Text Classification (Q)
|
93% |
2620
3.52 KIPS |
|
Machine Translation (SP)
|
100% |
3365
58.0 IPS |
|
Machine Translation (HP)
|
100% |
7191
123.9 IPS |
|
Machine Translation (Q)
|
98% |
8259
142.7 IPS |