Upload Date | September 14 2025 09:24 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPhone 13 mini |
Model ID | iPhone14,4 |
Motherboard | D16AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.59 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1356
252.2 IPS |
|
Image Classification (HP)
|
100% |
8200
1.52 KIPS |
|
Image Classification (Q)
|
96% |
11055
2.06 KIPS |
|
Image Segmentation (SP)
|
100% |
1307
21.2 IPS |
|
Image Segmentation (HP)
|
100% |
13103
212.4 IPS |
|
Image Segmentation (Q)
|
99% |
15478
250.9 IPS |
|
Pose Estimation (SP)
|
100% |
6284
7.33 IPS |
|
Pose Estimation (HP)
|
100% |
93701
109.3 IPS |
|
Pose Estimation (Q)
|
95% |
96431
113.0 IPS |
|
Object Detection (SP)
|
100% |
1427
113.2 IPS |
|
Object Detection (HP)
|
99% |
11065
880.2 IPS |
|
Object Detection (Q)
|
91% |
12073
964.7 IPS |
|
Face Detection (SP)
|
100% |
2755
32.7 IPS |
|
Face Detection (HP)
|
100% |
27677
328.9 IPS |
|
Face Detection (Q)
|
100% |
36237
430.6 IPS |
|
Depth Estimation (SP)
|
100% |
5292
40.8 IPS |
|
Depth Estimation (HP)
|
99% |
55413
426.9 IPS |
|
Depth Estimation (Q)
|
85% |
74279
580.5 IPS |
|
Style Transfer (SP)
|
100% |
16964
21.8 IPS |
|
Style Transfer (HP)
|
100% |
167569
215.4 IPS |
|
Style Transfer (Q)
|
96% |
170544
220.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3775
139.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
28653
1.06 KIPS |
|
Image Super-Resolution (Q)
|
99% |
28326
1.05 KIPS |
|
Text Classification (SP)
|
100% |
2425
3.24 KIPS |
|
Text Classification (HP)
|
100% |
2397
3.20 KIPS |
|
Text Classification (Q)
|
93% |
2442
3.28 KIPS |
|
Machine Translation (SP)
|
100% |
3620
62.4 IPS |
|
Machine Translation (HP)
|
100% |
6399
110.2 IPS |
|
Machine Translation (Q)
|
98% |
7662
132.4 IPS |