| Upload Date | October 26 2025 02:43 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,1 |
| Motherboard | J310AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.92 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.77 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
639
118.8 IPS |
|
|
Image Classification (HP)
|
100% |
671
124.7 IPS |
|
|
Image Classification (Q)
|
96% |
663
123.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
2680
43.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
2570
41.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
2568
41.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
10879
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
12118
14.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
11631
13.6 IPS |
|
|
Object Detection (SP)
|
100% |
1025
81.3 IPS |
|
|
Object Detection (HP)
|
100% |
1174
93.1 IPS |
|
|
Object Detection (Q)
|
92% |
965
77.0 IPS |
|
|
Face Detection (SP)
|
100% |
4011
47.7 IPS |
|
|
Face Detection (HP)
|
100% |
4145
49.2 IPS |
|
|
Face Detection (Q)
|
100% |
4058
48.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
7765
59.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
8392
64.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
7635
59.6 IPS |
|
|
Style Transfer (SP)
|
100% |
18026
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
22121
28.4 IPS |
|
|
Style Transfer (Q)
|
96% |
21030
27.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2932
108.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2802
103.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2749
101.5 IPS |
|
|
Text Classification (SP)
|
100% |
2558
3.41 KIPS |
|
|
Text Classification (HP)
|
99% |
4339
5.79 KIPS |
|
|
Text Classification (Q)
|
93% |
4366
5.86 KIPS |
|
|
Machine Translation (SP)
|
100% |
825
14.2 IPS |
|
|
Machine Translation (HP)
|
100% |
883
15.2 IPS |
|
|
Machine Translation (Q)
|
98% |
876
15.1 IPS |