User | iPhil |
Upload Date | March 22 2025 02:01 PM |
Views | 5 |
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% |
2088
388.2 IPS |
|
Image Classification (HP)
|
100% |
18094
3.36 KIPS |
|
Image Classification (Q)
|
97% |
27806
5.19 KIPS |
|
Image Segmentation (SP)
|
100% |
2212
35.9 IPS |
|
Image Segmentation (HP)
|
100% |
22151
359.1 IPS |
|
Image Segmentation (Q)
|
99% |
30653
496.9 IPS |
|
Pose Estimation (SP)
|
100% |
10024
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123485
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
232427
272.4 IPS |
|
Object Detection (SP)
|
100% |
2428
192.6 IPS |
|
Object Detection (HP)
|
100% |
18612
1.48 KIPS |
|
Object Detection (Q)
|
91% |
25998
2.08 KIPS |
|
Face Detection (SP)
|
100% |
4333
51.5 IPS |
|
Face Detection (HP)
|
100% |
43503
516.9 IPS |
|
Face Detection (Q)
|
100% |
63940
759.7 IPS |
|
Depth Estimation (SP)
|
100% |
8639
66.6 IPS |
|
Depth Estimation (HP)
|
99% |
99528
766.8 IPS |
|
Depth Estimation (Q)
|
85% |
167040
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
21562
27.7 IPS |
|
Style Transfer (HP)
|
100% |
234077
300.9 IPS |
|
Style Transfer (Q)
|
96% |
300359
387.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
6140
226.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
49440
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86447
3.19 KIPS |
|
Text Classification (SP)
|
100% |
2956
3.95 KIPS |
|
Text Classification (HP)
|
100% |
6430
8.58 KIPS |
|
Text Classification (Q)
|
93% |
6919
9.29 KIPS |
|
Machine Translation (SP)
|
100% |
4417
76.1 IPS |
|
Machine Translation (HP)
|
100% |
16757
288.6 IPS |
|
Machine Translation (Q)
|
98% |
18310
316.4 IPS |