Upload Date | September 21 2025 09:29 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
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 | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1324
246.2 IPS |
|
Image Classification (HP)
|
100% |
9254
1.72 KIPS |
|
Image Classification (Q)
|
97% |
11903
2.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1378
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
16089
260.8 IPS |
|
Image Segmentation (Q)
|
99% |
18977
307.6 IPS |
|
Pose Estimation (SP)
|
100% |
6136
7.16 IPS |
|
Pose Estimation (HP)
|
100% |
97982
114.3 IPS |
|
Pose Estimation (Q)
|
95% |
102637
120.3 IPS |
|
Object Detection (SP)
|
100% |
1460
115.8 IPS |
|
Object Detection (HP)
|
100% |
12377
981.7 IPS |
|
Object Detection (Q)
|
91% |
14211
1.14 KIPS |
|
Face Detection (SP)
|
100% |
3103
36.9 IPS |
|
Face Detection (HP)
|
100% |
30699
364.8 IPS |
|
Face Detection (Q)
|
100% |
40081
476.3 IPS |
|
Depth Estimation (SP)
|
100% |
5906
45.5 IPS |
|
Depth Estimation (HP)
|
99% |
72031
555.0 IPS |
|
Depth Estimation (Q)
|
85% |
92749
725.2 IPS |
|
Style Transfer (SP)
|
100% |
18000
23.1 IPS |
|
Style Transfer (HP)
|
100% |
172703
222.0 IPS |
|
Style Transfer (Q)
|
96% |
171321
221.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3859
142.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
32697
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35208
1.30 KIPS |
|
Text Classification (SP)
|
100% |
2772
3.70 KIPS |
|
Text Classification (HP)
|
100% |
2676
3.57 KIPS |
|
Text Classification (Q)
|
93% |
2761
3.71 KIPS |
|
Machine Translation (SP)
|
100% |
3391
58.4 IPS |
|
Machine Translation (HP)
|
100% |
7112
122.5 IPS |
|
Machine Translation (Q)
|
98% |
8494
146.8 IPS |