User | iPhil |
Upload Date | March 22 2025 01:59 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.4 |
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% |
2083
387.4 IPS |
|
Image Classification (HP)
|
100% |
18175
3.38 KIPS |
|
Image Classification (Q)
|
97% |
27949
5.22 KIPS |
|
Image Segmentation (SP)
|
100% |
2213
35.9 IPS |
|
Image Segmentation (HP)
|
100% |
22271
361.0 IPS |
|
Image Segmentation (Q)
|
99% |
30805
499.4 IPS |
|
Pose Estimation (SP)
|
100% |
9967
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
123112
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
230604
270.3 IPS |
|
Object Detection (SP)
|
100% |
2420
192.0 IPS |
|
Object Detection (HP)
|
100% |
18894
1.50 KIPS |
|
Object Detection (Q)
|
91% |
26050
2.08 KIPS |
|
Face Detection (SP)
|
100% |
4317
51.3 IPS |
|
Face Detection (HP)
|
100% |
42468
504.6 IPS |
|
Face Detection (Q)
|
100% |
64117
761.8 IPS |
|
Depth Estimation (SP)
|
100% |
8612
66.3 IPS |
|
Depth Estimation (HP)
|
99% |
99047
763.1 IPS |
|
Depth Estimation (Q)
|
85% |
167707
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
21934
28.2 IPS |
|
Style Transfer (HP)
|
100% |
232674
299.1 IPS |
|
Style Transfer (Q)
|
96% |
298913
385.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6075
224.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
48978
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87876
3.24 KIPS |
|
Text Classification (SP)
|
100% |
2941
3.93 KIPS |
|
Text Classification (HP)
|
100% |
6842
9.13 KIPS |
|
Text Classification (Q)
|
93% |
6520
8.75 KIPS |
|
Machine Translation (SP)
|
100% |
4460
76.8 IPS |
|
Machine Translation (HP)
|
100% |
16387
282.3 IPS |
|
Machine Translation (Q)
|
98% |
17997
311.0 IPS |