| Upload Date | November 21 2026 03:44 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.7.1 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.88 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
340
63.3 IPS |
|
|
Image Classification (HP)
|
100% |
640
119.0 IPS |
|
|
Image Classification (Q)
|
96% |
524
97.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
378
6.13 IPS |
|
|
Image Segmentation (HP)
|
100% |
646
10.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
726
11.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
1020
1.19 IPS |
|
|
Pose Estimation (HP)
|
100% |
908
1.06 IPS |
|
|
Pose Estimation (Q)
|
96% |
926
1.08 IPS |
|
|
Object Detection (SP)
|
100% |
313
24.9 IPS |
|
|
Object Detection (HP)
|
99% |
650
51.6 IPS |
|
|
Object Detection (Q)
|
92% |
536
42.7 IPS |
|
|
Face Detection (SP)
|
100% |
820
9.74 IPS |
|
|
Face Detection (HP)
|
100% |
1761
20.9 IPS |
|
|
Face Detection (Q)
|
100% |
1186
14.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
777
5.99 IPS |
|
|
Depth Estimation (HP)
|
98% |
1437
11.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
1353
10.6 IPS |
|
|
Style Transfer (SP)
|
100% |
2087
2.68 IPS |
|
|
Style Transfer (HP)
|
100% |
3617
4.65 IPS |
|
|
Style Transfer (Q)
|
96% |
3296
4.25 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
605
22.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
802
29.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
683
25.2 IPS |
|
|
Text Classification (SP)
|
100% |
477
636.1 IPS |
|
|
Text Classification (HP)
|
99% |
923
1.23 KIPS |
|
|
Text Classification (Q)
|
93% |
918
1.23 KIPS |
|
|
Machine Translation (SP)
|
100% |
569
9.80 IPS |
|
|
Machine Translation (HP)
|
99% |
985
17.0 IPS |
|
|
Machine Translation (Q)
|
98% |
960
16.6 IPS |