| Upload Date | October 26 2025 06:44 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 11 |
| Model ID | iPhone12,1 |
| Motherboard | N104AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.76 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
795
147.9 IPS |
|
|
Image Classification (HP)
|
100% |
1346
250.3 IPS |
|
|
Image Classification (Q)
|
96% |
975
182.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
847
13.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
1232
20.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
1449
23.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
3366
3.93 IPS |
|
|
Pose Estimation (HP)
|
100% |
6147
7.17 IPS |
|
|
Pose Estimation (Q)
|
95% |
5439
6.38 IPS |
|
|
Object Detection (SP)
|
100% |
770
61.1 IPS |
|
|
Object Detection (HP)
|
97% |
1569
124.9 IPS |
|
|
Object Detection (Q)
|
94% |
1143
91.1 IPS |
|
|
Face Detection (SP)
|
100% |
1635
19.4 IPS |
|
|
Face Detection (HP)
|
100% |
3153
37.5 IPS |
|
|
Face Detection (Q)
|
100% |
1766
21.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
2886
22.2 IPS |
|
|
Depth Estimation (HP)
|
97% |
5716
44.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
3094
24.2 IPS |
|
|
Style Transfer (SP)
|
100% |
6146
7.90 IPS |
|
|
Style Transfer (HP)
|
100% |
13481
17.3 IPS |
|
|
Style Transfer (Q)
|
96% |
11335
14.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1831
67.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2739
101.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2053
75.8 IPS |
|
|
Text Classification (SP)
|
100% |
1421
1.90 KIPS |
|
|
Text Classification (HP)
|
99% |
2242
2.99 KIPS |
|
|
Text Classification (Q)
|
93% |
2246
3.01 KIPS |
|
|
Machine Translation (SP)
|
100% |
964
16.6 IPS |
|
|
Machine Translation (HP)
|
98% |
3009
52.0 IPS |
|
|
Machine Translation (Q)
|
98% |
2856
49.4 IPS |