| User | tokris |
| Upload Date | July 20 2026 03:46 PM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.5.2 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,11 |
| Motherboard | J523xAP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 15.34 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2114
393.1 IPS |
|
|
Image Classification (HP)
|
100% |
1967
365.8 IPS |
|
|
Image Classification (Q)
|
94% |
1984
370.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
3992
64.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
4287
69.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
4088
66.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
17306
20.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
19482
22.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
18815
22.0 IPS |
|
|
Object Detection (SP)
|
100% |
2697
214.0 IPS |
|
|
Object Detection (HP)
|
100% |
2746
217.8 IPS |
|
|
Object Detection (Q)
|
91% |
2652
212.0 IPS |
|
|
Face Detection (SP)
|
100% |
7078
84.1 IPS |
|
|
Face Detection (HP)
|
100% |
8983
106.7 IPS |
|
|
Face Detection (Q)
|
100% |
8075
95.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
12481
96.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
13839
106.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
12983
101.5 IPS |
|
|
Style Transfer (SP)
|
100% |
29846
38.4 IPS |
|
|
Style Transfer (HP)
|
100% |
35809
46.0 IPS |
|
|
Style Transfer (Q)
|
96% |
34623
44.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6357
234.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7269
268.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5894
217.7 IPS |
|
|
Text Classification (SP)
|
100% |
4508
6.02 KIPS |
|
|
Text Classification (HP)
|
100% |
7121
9.51 KIPS |
|
|
Text Classification (Q)
|
92% |
7077
9.51 KIPS |
|
|
Machine Translation (SP)
|
100% |
1339
23.1 IPS |
|
|
Machine Translation (HP)
|
100% |
1426
24.6 IPS |
|
|
Machine Translation (Q)
|
98% |
1202
20.8 IPS |