Upload Date | September 19 2025 10:36 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% |
1321
245.6 IPS |
|
Image Classification (HP)
|
100% |
9515
1.77 KIPS |
|
Image Classification (Q)
|
97% |
11394
2.13 KIPS |
|
Image Segmentation (SP)
|
100% |
1399
22.7 IPS |
|
Image Segmentation (HP)
|
100% |
13803
223.7 IPS |
|
Image Segmentation (Q)
|
99% |
19009
308.1 IPS |
|
Pose Estimation (SP)
|
100% |
6054
7.06 IPS |
|
Pose Estimation (HP)
|
100% |
99233
115.8 IPS |
|
Pose Estimation (Q)
|
95% |
101471
118.9 IPS |
|
Object Detection (SP)
|
100% |
1447
114.8 IPS |
|
Object Detection (HP)
|
100% |
12142
963.1 IPS |
|
Object Detection (Q)
|
91% |
14274
1.14 KIPS |
|
Face Detection (SP)
|
100% |
3157
37.5 IPS |
|
Face Detection (HP)
|
100% |
30343
360.5 IPS |
|
Face Detection (Q)
|
100% |
39998
475.3 IPS |
|
Depth Estimation (SP)
|
100% |
5915
45.6 IPS |
|
Depth Estimation (HP)
|
99% |
72530
558.8 IPS |
|
Depth Estimation (Q)
|
85% |
90672
708.9 IPS |
|
Style Transfer (SP)
|
100% |
18041
23.2 IPS |
|
Style Transfer (HP)
|
100% |
173998
223.7 IPS |
|
Style Transfer (Q)
|
96% |
173234
223.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3861
142.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
32379
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36195
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2808
3.75 KIPS |
|
Text Classification (HP)
|
100% |
2819
3.76 KIPS |
|
Text Classification (Q)
|
93% |
2907
3.90 KIPS |
|
Machine Translation (SP)
|
100% |
3367
58.0 IPS |
|
Machine Translation (HP)
|
100% |
7251
124.9 IPS |
|
Machine Translation (Q)
|
98% |
8441
145.9 IPS |