| User | Neo8680 |
| Upload Date | April 07 2025 12:28 AM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 18.4 |
| 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% |
2081
386.9 IPS |
|
|
Image Classification (HP)
|
100% |
17722
3.30 KIPS |
|
|
Image Classification (Q)
|
97% |
24606
4.59 KIPS |
|
|
Image Segmentation (SP)
|
100% |
2172
35.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
22190
359.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
30281
490.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
10072
11.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
122914
143.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
231512
271.3 IPS |
|
|
Object Detection (SP)
|
100% |
2418
191.8 IPS |
|
|
Object Detection (HP)
|
100% |
18224
1.45 KIPS |
|
|
Object Detection (Q)
|
91% |
25643
2.05 KIPS |
|
|
Face Detection (SP)
|
100% |
4323
51.4 IPS |
|
|
Face Detection (HP)
|
100% |
42672
507.0 IPS |
|
|
Face Detection (Q)
|
100% |
63652
756.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
8594
66.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
99231
764.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
166940
1.31 KIPS |
|
|
Style Transfer (SP)
|
100% |
21835
28.1 IPS |
|
|
Style Transfer (HP)
|
100% |
234993
302.1 IPS |
|
|
Style Transfer (Q)
|
96% |
297733
384.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6046
223.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
48738
1.80 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
84600
3.12 KIPS |
|
|
Text Classification (SP)
|
100% |
2909
3.88 KIPS |
|
|
Text Classification (HP)
|
100% |
7234
9.66 KIPS |
|
|
Text Classification (Q)
|
93% |
6475
8.69 KIPS |
|
|
Machine Translation (SP)
|
100% |
4400
75.8 IPS |
|
|
Machine Translation (HP)
|
100% |
16294
280.7 IPS |
|
|
Machine Translation (Q)
|
98% |
17860
308.7 IPS |