| Upload Date | November 21 2026 04:55 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 27.3 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,2 |
| Motherboard | J311AP |
| 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% |
645
120.0 IPS |
|
|
Image Classification (HP)
|
100% |
644
119.7 IPS |
|
|
Image Classification (Q)
|
94% |
605
113.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
2607
42.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
2727
44.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
2650
43.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
10777
12.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
11986
14.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
11700
13.7 IPS |
|
|
Object Detection (SP)
|
100% |
986
78.2 IPS |
|
|
Object Detection (HP)
|
100% |
1169
92.8 IPS |
|
|
Object Detection (Q)
|
91% |
992
79.3 IPS |
|
|
Face Detection (SP)
|
100% |
4333
51.5 IPS |
|
|
Face Detection (HP)
|
100% |
4088
48.6 IPS |
|
|
Face Detection (Q)
|
100% |
4330
51.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7274
56.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
7604
58.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
7194
56.3 IPS |
|
|
Style Transfer (SP)
|
100% |
17888
23.0 IPS |
|
|
Style Transfer (HP)
|
100% |
21784
28.0 IPS |
|
|
Style Transfer (Q)
|
96% |
21044
27.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2890
106.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2662
98.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2688
99.3 IPS |
|
|
Text Classification (SP)
|
100% |
4468
5.96 KIPS |
|
|
Text Classification (HP)
|
99% |
7124
9.51 KIPS |
|
|
Text Classification (Q)
|
93% |
7018
9.42 KIPS |
|
|
Machine Translation (SP)
|
100% |
884
15.2 IPS |
|
|
Machine Translation (HP)
|
100% |
981
16.9 IPS |
|
|
Machine Translation (Q)
|
98% |
989
17.1 IPS |