| User | M4rc0L |
| Upload Date | September 17 2025 07:52 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| 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% |
380
70.7 IPS |
|
|
Image Classification (HP)
|
100% |
643
119.6 IPS |
|
|
Image Classification (Q)
|
96% |
525
98.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
407
6.60 IPS |
|
|
Image Segmentation (HP)
|
100% |
697
11.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
758
12.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
1092
1.27 IPS |
|
|
Pose Estimation (HP)
|
100% |
1022
1.19 IPS |
|
|
Pose Estimation (Q)
|
96% |
1019
1.19 IPS |
|
|
Object Detection (SP)
|
100% |
338
26.8 IPS |
|
|
Object Detection (HP)
|
99% |
688
54.6 IPS |
|
|
Object Detection (Q)
|
92% |
550
43.9 IPS |
|
|
Face Detection (SP)
|
100% |
882
10.5 IPS |
|
|
Face Detection (HP)
|
100% |
1761
20.9 IPS |
|
|
Face Detection (Q)
|
100% |
1193
14.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
885
6.82 IPS |
|
|
Depth Estimation (HP)
|
98% |
1628
12.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
1394
10.9 IPS |
|
|
Style Transfer (SP)
|
100% |
2270
2.92 IPS |
|
|
Style Transfer (HP)
|
100% |
3833
4.93 IPS |
|
|
Style Transfer (Q)
|
96% |
3444
4.45 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
632
23.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
832
30.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
692
25.6 IPS |
|
|
Text Classification (SP)
|
100% |
292
389.1 IPS |
|
|
Text Classification (HP)
|
100% |
567
756.9 IPS |
|
|
Text Classification (Q)
|
93% |
563
755.6 IPS |
|
|
Machine Translation (SP)
|
100% |
585
10.1 IPS |
|
|
Machine Translation (HP)
|
99% |
976
16.8 IPS |
|
|
Machine Translation (Q)
|
98% |
981
17.0 IPS |