| User | jdklev |
| Upload Date | February 07 2025 07:53 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad Pro 11-inch (M4) |
| Model ID | iPad16,4 |
| Motherboard | J718AP |
| 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% |
2007
373.2 IPS |
|
|
Image Classification (HP)
|
100% |
3350
623.1 IPS |
|
|
Image Classification (Q)
|
96% |
2298
429.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
2129
34.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
3318
53.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
3589
58.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
9999
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
19114
22.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
16124
18.9 IPS |
|
|
Object Detection (SP)
|
100% |
2244
178.0 IPS |
|
|
Object Detection (HP)
|
97% |
3788
301.5 IPS |
|
|
Object Detection (Q)
|
94% |
2674
213.1 IPS |
|
|
Face Detection (SP)
|
100% |
3976
47.2 IPS |
|
|
Face Detection (HP)
|
100% |
7755
92.1 IPS |
|
|
Face Detection (Q)
|
100% |
4421
52.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
8316
64.1 IPS |
|
|
Depth Estimation (HP)
|
97% |
14670
113.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
10190
79.5 IPS |
|
|
Style Transfer (SP)
|
100% |
25135
32.3 IPS |
|
|
Style Transfer (HP)
|
100% |
38115
49.0 IPS |
|
|
Style Transfer (Q)
|
96% |
31326
40.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5877
217.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6959
256.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4855
179.3 IPS |
|
|
Text Classification (SP)
|
100% |
3035
4.05 KIPS |
|
|
Text Classification (HP)
|
100% |
5527
7.38 KIPS |
|
|
Text Classification (Q)
|
93% |
5468
7.34 KIPS |
|
|
Machine Translation (SP)
|
0
|
||
|
Machine Translation (HP)
|
98% |
6840
118.2 IPS |
|
|
Machine Translation (Q)
|
98% |
6726
116.2 IPS |