User | iPhil |
Upload Date | March 22 2025 02:15 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% |
2060
383.1 IPS |
|
Image Classification (HP)
|
100% |
17814
3.31 KIPS |
|
Image Classification (Q)
|
97% |
25713
4.80 KIPS |
|
Image Segmentation (SP)
|
100% |
2192
35.5 IPS |
|
Image Segmentation (HP)
|
100% |
22108
358.4 IPS |
|
Image Segmentation (Q)
|
99% |
30306
491.3 IPS |
|
Pose Estimation (SP)
|
100% |
10017
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
122729
143.2 IPS |
|
Pose Estimation (Q)
|
95% |
231525
271.4 IPS |
|
Object Detection (SP)
|
100% |
2409
191.1 IPS |
|
Object Detection (HP)
|
100% |
18246
1.45 KIPS |
|
Object Detection (Q)
|
91% |
25600
2.05 KIPS |
|
Face Detection (SP)
|
100% |
4309
51.2 IPS |
|
Face Detection (HP)
|
100% |
42315
502.8 IPS |
|
Face Detection (Q)
|
100% |
62949
748.0 IPS |
|
Depth Estimation (SP)
|
100% |
8607
66.3 IPS |
|
Depth Estimation (HP)
|
99% |
98867
761.7 IPS |
|
Depth Estimation (Q)
|
85% |
168042
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
21699
27.9 IPS |
|
Style Transfer (HP)
|
100% |
231802
298.0 IPS |
|
Style Transfer (Q)
|
96% |
298905
385.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6121
226.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
49127
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83651
3.09 KIPS |
|
Text Classification (SP)
|
100% |
2920
3.90 KIPS |
|
Text Classification (HP)
|
100% |
6141
8.20 KIPS |
|
Text Classification (Q)
|
93% |
6264
8.41 KIPS |
|
Machine Translation (SP)
|
100% |
4411
76.0 IPS |
|
Machine Translation (HP)
|
100% |
16308
280.9 IPS |
|
Machine Translation (Q)
|
98% |
17953
310.2 IPS |