| Upload Date | October 26 2025 02:30 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% |
686
127.6 IPS |
|
|
Image Classification (HP)
|
100% |
635
118.1 IPS |
|
|
Image Classification (Q)
|
96% |
581
108.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
2544
41.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2654
43.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
2547
41.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
10898
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
12204
14.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
11744
13.8 IPS |
|
|
Object Detection (SP)
|
100% |
1119
88.8 IPS |
|
|
Object Detection (HP)
|
100% |
1151
91.3 IPS |
|
|
Object Detection (Q)
|
92% |
1043
83.3 IPS |
|
|
Face Detection (SP)
|
100% |
4029
47.9 IPS |
|
|
Face Detection (HP)
|
100% |
4084
48.5 IPS |
|
|
Face Detection (Q)
|
100% |
4256
50.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
7784
60.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
8400
64.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
7675
59.9 IPS |
|
|
Style Transfer (SP)
|
100% |
17960
23.1 IPS |
|
|
Style Transfer (HP)
|
100% |
22142
28.5 IPS |
|
|
Style Transfer (Q)
|
96% |
20830
26.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2788
102.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2734
100.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2726
100.7 IPS |
|
|
Text Classification (SP)
|
100% |
2534
3.38 KIPS |
|
|
Text Classification (HP)
|
99% |
4349
5.81 KIPS |
|
|
Text Classification (Q)
|
93% |
4322
5.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
837
14.4 IPS |
|
|
Machine Translation (HP)
|
100% |
888
15.3 IPS |
|
|
Machine Translation (Q)
|
98% |
887
15.3 IPS |