| User | F4T4L1TY |
| Upload Date | February 22 2026 03:45 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
1213
225.7 IPS |
|
|
Image Classification (HP)
|
100% |
4879
907.3 IPS |
|
|
Image Classification (Q)
|
97% |
5001
933.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1094
17.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
8151
132.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
8658
140.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
4704
5.49 IPS |
|
|
Pose Estimation (HP)
|
100% |
63361
73.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
61227
71.8 IPS |
|
|
Object Detection (SP)
|
100% |
1148
91.1 IPS |
|
|
Object Detection (HP)
|
99% |
6048
481.1 IPS |
|
|
Object Detection (Q)
|
89% |
4915
393.4 IPS |
|
|
Face Detection (SP)
|
100% |
2496
29.7 IPS |
|
|
Face Detection (HP)
|
100% |
12515
148.7 IPS |
|
|
Face Detection (Q)
|
100% |
10306
122.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
4641
35.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
37695
290.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
35990
281.5 IPS |
|
|
Style Transfer (SP)
|
100% |
12684
16.3 IPS |
|
|
Style Transfer (HP)
|
100% |
96893
124.6 IPS |
|
|
Style Transfer (Q)
|
96% |
92081
118.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2631
97.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18597
686.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
18798
694.1 IPS |
|
|
Text Classification (SP)
|
100% |
3902
5.21 KIPS |
|
|
Text Classification (HP)
|
100% |
2231
2.98 KIPS |
|
|
Text Classification (Q)
|
93% |
2316
3.11 KIPS |
|
|
Machine Translation (SP)
|
100% |
2250
38.8 IPS |
|
|
Machine Translation (HP)
|
100% |
3425
59.0 IPS |
|
|
Machine Translation (Q)
|
98% |
4146
71.6 IPS |