| Upload Date | February 07 2026 04:02 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.2.1 |
| 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% |
2099
390.4 IPS |
|
|
Image Classification (HP)
|
100% |
17552
3.26 KIPS |
|
|
Image Classification (Q)
|
97% |
27273
5.09 KIPS |
|
|
Image Segmentation (SP)
|
100% |
2180
35.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
22430
363.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
30781
499.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
10095
11.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
123533
144.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
232521
272.5 IPS |
|
|
Object Detection (SP)
|
100% |
2456
194.8 IPS |
|
|
Object Detection (HP)
|
100% |
18545
1.47 KIPS |
|
|
Object Detection (Q)
|
91% |
25915
2.07 KIPS |
|
|
Face Detection (SP)
|
100% |
4319
51.3 IPS |
|
|
Face Detection (HP)
|
100% |
43558
517.6 IPS |
|
|
Face Detection (Q)
|
100% |
62984
748.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
8552
65.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
98980
762.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
163266
1.28 KIPS |
|
|
Style Transfer (SP)
|
100% |
24349
31.3 IPS |
|
|
Style Transfer (HP)
|
100% |
232593
299.0 IPS |
|
|
Style Transfer (Q)
|
96% |
320858
414.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6055
223.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
51109
1.89 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
83944
3.10 KIPS |
|
|
Text Classification (SP)
|
100% |
3241
4.33 KIPS |
|
|
Text Classification (HP)
|
99% |
5550
7.41 KIPS |
|
|
Text Classification (Q)
|
93% |
5641
7.57 KIPS |
|
|
Machine Translation (SP)
|
100% |
4543
78.3 IPS |
|
|
Machine Translation (HP)
|
100% |
16574
285.5 IPS |
|
|
Machine Translation (Q)
|
98% |
18263
315.6 IPS |