| Upload Date | November 21 2026 08:11 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.7.3 |
| Model | iPad Pro 13-inch (M4) |
| Model ID | iPad16,6 |
| Motherboard | J721AP |
| 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 | 7.21 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2088
388.3 IPS |
|
|
Image Classification (HP)
|
100% |
16883
3.14 KIPS |
|
|
Image Classification (Q)
|
97% |
24878
4.64 KIPS |
|
|
Image Segmentation (SP)
|
100% |
2234
36.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
22322
361.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
32032
519.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
8868
10.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
122920
143.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
232412
272.4 IPS |
|
|
Object Detection (SP)
|
100% |
2481
196.8 IPS |
|
|
Object Detection (HP)
|
100% |
17728
1.41 KIPS |
|
|
Object Detection (Q)
|
89% |
26565
2.13 KIPS |
|
|
Face Detection (SP)
|
100% |
4543
54.0 IPS |
|
|
Face Detection (HP)
|
100% |
44098
524.0 IPS |
|
|
Face Detection (Q)
|
100% |
71870
854.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
8143
62.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
98759
760.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
170387
1.33 KIPS |
|
|
Style Transfer (SP)
|
100% |
22926
29.5 IPS |
|
|
Style Transfer (HP)
|
100% |
232652
299.1 IPS |
|
|
Style Transfer (Q)
|
96% |
291640
376.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5305
195.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
52716
1.95 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
82769
3.06 KIPS |
|
|
Text Classification (SP)
|
100% |
6192
8.26 KIPS |
|
|
Text Classification (HP)
|
100% |
9943
13.3 KIPS |
|
|
Text Classification (Q)
|
93% |
9691
13.0 KIPS |
|
|
Machine Translation (SP)
|
100% |
4449
76.6 IPS |
|
|
Machine Translation (HP)
|
100% |
16483
283.9 IPS |
|
|
Machine Translation (Q)
|
98% |
18094
312.7 IPS |