| Upload Date | November 18 2025 07:49 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 12 |
| Model ID | iPhone13,2 |
| Motherboard | D53gAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1230
228.8 IPS |
|
|
Image Classification (HP)
|
100% |
2024
376.5 IPS |
|
|
Image Classification (Q)
|
96% |
1448
270.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1118
18.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1721
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2191
35.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
4701
5.49 IPS |
|
|
Pose Estimation (HP)
|
100% |
10011
11.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
8867
10.4 IPS |
|
|
Object Detection (SP)
|
100% |
1206
95.7 IPS |
|
|
Object Detection (HP)
|
97% |
2236
178.0 IPS |
|
|
Object Detection (Q)
|
94% |
1638
130.5 IPS |
|
|
Face Detection (SP)
|
100% |
2485
29.5 IPS |
|
|
Face Detection (HP)
|
100% |
4616
54.8 IPS |
|
|
Face Detection (Q)
|
100% |
2629
31.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4437
34.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
8763
67.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
6463
50.5 IPS |
|
|
Style Transfer (SP)
|
100% |
12122
15.6 IPS |
|
|
Style Transfer (HP)
|
100% |
20653
26.5 IPS |
|
|
Style Transfer (Q)
|
96% |
17940
23.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2525
93.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3964
146.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3173
117.2 IPS |
|
|
Text Classification (SP)
|
100% |
2307
3.08 KIPS |
|
|
Text Classification (HP)
|
99% |
3907
5.21 KIPS |
|
|
Text Classification (Q)
|
93% |
3870
5.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
2201
37.9 IPS |
|
|
Machine Translation (HP)
|
98% |
4248
73.4 IPS |
|
|
Machine Translation (Q)
|
98% |
4216
72.9 IPS |