| Upload Date | October 26 2025 02:55 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% |
677
125.9 IPS |
|
|
Image Classification (HP)
|
100% |
653
121.4 IPS |
|
|
Image Classification (Q)
|
96% |
614
114.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2470
40.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
2788
45.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
2537
41.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
10843
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
12117
14.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
11631
13.6 IPS |
|
|
Object Detection (SP)
|
100% |
1214
96.3 IPS |
|
|
Object Detection (HP)
|
100% |
969
76.9 IPS |
|
|
Object Detection (Q)
|
92% |
1091
87.1 IPS |
|
|
Face Detection (SP)
|
100% |
4186
49.7 IPS |
|
|
Face Detection (HP)
|
100% |
4198
49.9 IPS |
|
|
Face Detection (Q)
|
100% |
4329
51.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7842
60.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
7439
57.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
7346
57.4 IPS |
|
|
Style Transfer (SP)
|
100% |
18066
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
22132
28.5 IPS |
|
|
Style Transfer (Q)
|
96% |
20645
26.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2963
109.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2827
104.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2658
98.1 IPS |
|
|
Text Classification (SP)
|
100% |
2553
3.41 KIPS |
|
|
Text Classification (HP)
|
99% |
4344
5.80 KIPS |
|
|
Text Classification (Q)
|
93% |
4321
5.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
823
14.2 IPS |
|
|
Machine Translation (HP)
|
100% |
876
15.1 IPS |
|
|
Machine Translation (Q)
|
98% |
870
15.0 IPS |