User | CatCat |
Upload Date | September 16 2025 01:50 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 12 |
Model ID | iPhone13,2 |
Motherboard | D53gAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.60 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1226
228.1 IPS |
|
Image Classification (HP)
|
100% |
4979
925.9 IPS |
|
Image Classification (Q)
|
96% |
5059
944.8 IPS |
|
Image Segmentation (SP)
|
100% |
1117
18.1 IPS |
|
Image Segmentation (HP)
|
100% |
7827
126.9 IPS |
|
Image Segmentation (Q)
|
99% |
8125
131.7 IPS |
|
Pose Estimation (SP)
|
100% |
4693
5.48 IPS |
|
Pose Estimation (HP)
|
100% |
60422
70.5 IPS |
|
Pose Estimation (Q)
|
95% |
59464
69.7 IPS |
|
Object Detection (SP)
|
100% |
1183
93.9 IPS |
|
Object Detection (HP)
|
99% |
5332
424.1 IPS |
|
Object Detection (Q)
|
91% |
4692
374.9 IPS |
|
Face Detection (SP)
|
100% |
2462
29.3 IPS |
|
Face Detection (HP)
|
100% |
11626
138.1 IPS |
|
Face Detection (Q)
|
100% |
9815
116.6 IPS |
|
Depth Estimation (SP)
|
100% |
4485
34.6 IPS |
|
Depth Estimation (HP)
|
99% |
36448
280.8 IPS |
|
Depth Estimation (Q)
|
85% |
34273
267.8 IPS |
|
Style Transfer (SP)
|
100% |
12392
15.9 IPS |
|
Style Transfer (HP)
|
100% |
95118
122.3 IPS |
|
Style Transfer (Q)
|
96% |
91820
118.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
2547
94.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
18003
664.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
18685
689.9 IPS |
|
Text Classification (SP)
|
100% |
2298
3.07 KIPS |
|
Text Classification (HP)
|
100% |
2252
3.01 KIPS |
|
Text Classification (Q)
|
93% |
2450
3.29 KIPS |
|
Machine Translation (SP)
|
100% |
2241
38.6 IPS |
|
Machine Translation (HP)
|
100% |
3320
57.2 IPS |
|
Machine Translation (Q)
|
98% |
4189
72.4 IPS |