| User | Nuckell |
| Upload Date | December 02 2025 11:44 PM |
| Views | 16 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro 11-inch (M4) |
| Model ID | iPad16,3 |
| Motherboard | J717AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 10 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 15.14 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4618
858.9 IPS |
|
|
Image Classification (HP)
|
100% |
4946
919.8 IPS |
|
|
Image Classification (Q)
|
96% |
4486
837.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
7052
114.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
7951
128.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
7672
124.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
26942
31.4 IPS |
|
|
Pose Estimation (HP)
|
100% |
30955
36.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
30267
35.5 IPS |
|
|
Object Detection (SP)
|
100% |
4564
362.0 IPS |
|
|
Object Detection (HP)
|
100% |
5149
408.4 IPS |
|
|
Object Detection (Q)
|
92% |
4781
381.6 IPS |
|
|
Face Detection (SP)
|
100% |
12650
150.3 IPS |
|
|
Face Detection (HP)
|
100% |
16748
199.0 IPS |
|
|
Face Detection (Q)
|
100% |
13483
160.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
19964
153.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
22220
171.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
20373
159.1 IPS |
|
|
Style Transfer (SP)
|
100% |
55288
71.1 IPS |
|
|
Style Transfer (HP)
|
100% |
67060
86.2 IPS |
|
|
Style Transfer (Q)
|
96% |
64881
83.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11305
417.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11650
430.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10311
380.7 IPS |
|
|
Text Classification (SP)
|
100% |
3311
4.42 KIPS |
|
|
Text Classification (HP)
|
99% |
5611
7.49 KIPS |
|
|
Text Classification (Q)
|
93% |
5609
7.53 KIPS |
|
|
Machine Translation (SP)
|
100% |
4770
82.2 IPS |
|
|
Machine Translation (HP)
|
100% |
5069
87.3 IPS |
|
|
Machine Translation (Q)
|
98% |
2473
42.7 IPS |