| User | Bormot |
| Upload Date | December 06 2024 10:52 PM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| 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% |
4499
836.7 IPS |
|
|
Image Classification (HP)
|
100% |
4861
903.9 IPS |
|
|
Image Classification (Q)
|
97% |
4158
775.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
4892
79.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
6724
109.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
7148
115.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
28194
32.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
30062
35.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
28638
33.6 IPS |
|
|
Object Detection (SP)
|
100% |
4757
377.3 IPS |
|
|
Object Detection (HP)
|
100% |
5213
413.5 IPS |
|
|
Object Detection (Q)
|
91% |
4432
354.2 IPS |
|
|
Face Detection (SP)
|
100% |
12945
153.8 IPS |
|
|
Face Detection (HP)
|
100% |
16418
195.1 IPS |
|
|
Face Detection (Q)
|
100% |
11988
142.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
20454
157.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
22311
171.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
18996
148.5 IPS |
|
|
Style Transfer (SP)
|
100% |
58102
74.7 IPS |
|
|
Style Transfer (HP)
|
100% |
67852
87.2 IPS |
|
|
Style Transfer (Q)
|
96% |
63912
82.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11577
427.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
12640
466.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10357
382.4 IPS |
|
|
Text Classification (SP)
|
100% |
3002
4.01 KIPS |
|
|
Text Classification (HP)
|
100% |
5527
7.38 KIPS |
|
|
Text Classification (Q)
|
93% |
5574
7.48 KIPS |
|
|
Machine Translation (SP)
|
100% |
1946
33.5 IPS |
|
|
Machine Translation (HP)
|
100% |
1641
28.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1647
28.5 IPS |