| User | DeakonFrost |
| Upload Date | September 11 2025 08:48 PM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| Model | iPad Pro 11-inch (M4) |
| Model ID | iPad16,3 |
| Motherboard | J717AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.29 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4527
842.0 IPS |
|
|
Image Classification (HP)
|
100% |
4964
923.2 IPS |
|
|
Image Classification (Q)
|
96% |
4409
823.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
7142
115.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
8010
129.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
7698
124.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
27093
31.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
31029
36.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
30149
35.3 IPS |
|
|
Object Detection (SP)
|
100% |
4587
363.8 IPS |
|
|
Object Detection (HP)
|
100% |
5181
411.0 IPS |
|
|
Object Detection (Q)
|
92% |
4767
380.5 IPS |
|
|
Face Detection (SP)
|
100% |
12729
151.2 IPS |
|
|
Face Detection (HP)
|
100% |
16810
199.7 IPS |
|
|
Face Detection (Q)
|
100% |
13445
159.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
19934
153.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
22236
171.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
20128
157.2 IPS |
|
|
Style Transfer (SP)
|
100% |
55931
71.9 IPS |
|
|
Style Transfer (HP)
|
100% |
67107
86.3 IPS |
|
|
Style Transfer (Q)
|
96% |
65304
84.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11334
418.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11633
429.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10413
384.5 IPS |
|
|
Text Classification (SP)
|
100% |
3279
4.38 KIPS |
|
|
Text Classification (HP)
|
99% |
5845
7.80 KIPS |
|
|
Text Classification (Q)
|
93% |
5688
7.63 KIPS |
|
|
Machine Translation (SP)
|
100% |
4756
81.9 IPS |
|
|
Machine Translation (HP)
|
100% |
4639
79.9 IPS |
|
|
Machine Translation (Q)
|
98% |
4524
78.2 IPS |