Upload Date | September 17 2025 04:25 PM |
Views | 4 |
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% |
1333
247.8 IPS |
|
Image Classification (HP)
|
100% |
9366
1.74 KIPS |
|
Image Classification (Q)
|
97% |
11249
2.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1390
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
15860
257.1 IPS |
|
Image Segmentation (Q)
|
99% |
19048
308.8 IPS |
|
Pose Estimation (SP)
|
100% |
6400
7.47 IPS |
|
Pose Estimation (HP)
|
100% |
96706
112.8 IPS |
|
Pose Estimation (Q)
|
95% |
101896
119.4 IPS |
|
Object Detection (SP)
|
100% |
1469
116.6 IPS |
|
Object Detection (HP)
|
100% |
12242
971.0 IPS |
|
Object Detection (Q)
|
91% |
13955
1.12 KIPS |
|
Face Detection (SP)
|
100% |
3195
38.0 IPS |
|
Face Detection (HP)
|
100% |
30377
360.9 IPS |
|
Face Detection (Q)
|
100% |
39259
466.5 IPS |
|
Depth Estimation (SP)
|
100% |
5964
46.0 IPS |
|
Depth Estimation (HP)
|
99% |
69889
538.5 IPS |
|
Depth Estimation (Q)
|
85% |
89193
697.4 IPS |
|
Style Transfer (SP)
|
100% |
18486
23.8 IPS |
|
Style Transfer (HP)
|
100% |
169250
217.6 IPS |
|
Style Transfer (Q)
|
96% |
169084
218.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3854
142.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
31995
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
34866
1.29 KIPS |
|
Text Classification (SP)
|
100% |
2810
3.75 KIPS |
|
Text Classification (HP)
|
100% |
2635
3.52 KIPS |
|
Text Classification (Q)
|
93% |
2594
3.48 KIPS |
|
Machine Translation (SP)
|
100% |
3398
58.5 IPS |
|
Machine Translation (HP)
|
100% |
7257
125.0 IPS |
|
Machine Translation (Q)
|
98% |
8280
143.1 IPS |