| Upload Date | October 23 2025 11:05 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 26.0.1 |
| Model | iPad Pro (12.9-inch, 6th generation) |
| Model ID | iPad14,5 |
| Motherboard | J620AP |
| CPU Information | |
|---|---|
| Name | Apple M2 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 15.34 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
3684
685.2 IPS |
|
|
Image Classification (HP)
|
100% |
3722
692.2 IPS |
|
|
Image Classification (Q)
|
96% |
3407
636.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
5790
93.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
5962
96.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
5678
92.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
24742
28.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
26769
31.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
26056
30.5 IPS |
|
|
Object Detection (SP)
|
100% |
3584
284.3 IPS |
|
|
Object Detection (HP)
|
100% |
3598
285.4 IPS |
|
|
Object Detection (Q)
|
92% |
3409
272.1 IPS |
|
|
Face Detection (SP)
|
100% |
10373
123.3 IPS |
|
|
Face Detection (HP)
|
100% |
11968
142.2 IPS |
|
|
Face Detection (Q)
|
100% |
9961
118.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
16891
130.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
18177
140.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
16719
130.6 IPS |
|
|
Style Transfer (SP)
|
100% |
43154
55.5 IPS |
|
|
Style Transfer (HP)
|
100% |
49231
63.3 IPS |
|
|
Style Transfer (Q)
|
96% |
47716
61.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
9934
366.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
10357
382.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
8848
326.7 IPS |
|
|
Text Classification (SP)
|
100% |
2344
3.13 KIPS |
|
|
Text Classification (HP)
|
99% |
3914
5.22 KIPS |
|
|
Text Classification (Q)
|
93% |
3974
5.33 KIPS |
|
|
Machine Translation (SP)
|
100% |
1802
31.0 IPS |
|
|
Machine Translation (HP)
|
100% |
1932
33.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1889
32.6 IPS |