| User | FangYuan |
| Upload Date | June 14 2026 08:47 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 27.0 |
| 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 | 7.28 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4600
855.4 IPS |
|
|
Image Classification (HP)
|
100% |
4888
909.0 IPS |
|
|
Image Classification (Q)
|
96% |
4760
888.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
7460
120.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
8237
133.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
7825
126.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
27002
31.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
30897
36.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
30080
35.2 IPS |
|
|
Object Detection (SP)
|
100% |
4920
390.3 IPS |
|
|
Object Detection (HP)
|
100% |
5273
418.2 IPS |
|
|
Object Detection (Q)
|
91% |
4903
391.9 IPS |
|
|
Face Detection (SP)
|
100% |
13446
159.8 IPS |
|
|
Face Detection (HP)
|
100% |
17856
212.2 IPS |
|
|
Face Detection (Q)
|
100% |
16476
195.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
19626
151.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
22106
170.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
20645
161.5 IPS |
|
|
Style Transfer (SP)
|
100% |
57541
74.0 IPS |
|
|
Style Transfer (HP)
|
100% |
68482
88.0 IPS |
|
|
Style Transfer (Q)
|
96% |
65731
84.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11435
422.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11676
431.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10199
376.6 IPS |
|
|
Text Classification (SP)
|
100% |
6528
8.71 KIPS |
|
|
Text Classification (HP)
|
99% |
10058
13.4 KIPS |
|
|
Text Classification (Q)
|
93% |
10434
14.0 KIPS |
|
|
Machine Translation (SP)
|
100% |
4899
84.4 IPS |
|
|
Machine Translation (HP)
|
100% |
5325
91.7 IPS |
|
|
Machine Translation (Q)
|
98% |
4736
81.8 IPS |