| User | mwickens |
| Upload Date | June 23 2026 03:53 AM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 27.0 |
| Model | iPad17,3 |
| Model ID | iPad17,3 |
| Motherboard | J820AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 10 Cores |
| Identifier | ARM |
| Base Frequency | 4.42 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 15.02 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2322
431.9 IPS |
|
|
Image Classification (HP)
|
100% |
4453
828.2 IPS |
|
|
Image Classification (Q)
|
94% |
2514
469.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
2235
36.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
3222
52.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
3756
60.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
10783
12.6 IPS |
|
|
Pose Estimation (HP)
|
99% |
23996
28.0 IPS |
|
|
Pose Estimation (Q)
|
97% |
20017
23.4 IPS |
|
|
Object Detection (SP)
|
100% |
2744
217.7 IPS |
|
|
Object Detection (HP)
|
98% |
4931
392.4 IPS |
|
|
Object Detection (Q)
|
88% |
3168
253.9 IPS |
|
|
Face Detection (SP)
|
100% |
5300
63.0 IPS |
|
|
Face Detection (HP)
|
100% |
10132
120.4 IPS |
|
|
Face Detection (Q)
|
100% |
5173
61.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
9021
69.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
15169
117.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
9883
77.2 IPS |
|
|
Style Transfer (SP)
|
100% |
26351
33.9 IPS |
|
|
Style Transfer (HP)
|
100% |
47057
60.5 IPS |
|
|
Style Transfer (Q)
|
96% |
37488
48.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6498
239.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11871
438.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6867
253.6 IPS |
|
|
Text Classification (SP)
|
100% |
5952
7.94 KIPS |
|
|
Text Classification (HP)
|
99% |
10007
13.4 KIPS |
|
|
Text Classification (Q)
|
93% |
10083
13.5 KIPS |
|
|
Machine Translation (SP)
|
100% |
5065
87.3 IPS |
|
|
Machine Translation (HP)
|
100% |
8618
148.4 IPS |
|
|
Machine Translation (Q)
|
98% |
8561
147.9 IPS |