| Upload Date | November 21 2026 02:18 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.6 |
| 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
228.7 IPS |
|
|
Image Classification (HP)
|
100% |
2037
378.8 IPS |
|
|
Image Classification (Q)
|
96% |
1456
271.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
1128
18.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
1761
28.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
2203
35.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
5019
5.86 IPS |
|
|
Pose Estimation (HP)
|
100% |
10857
12.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
9583
11.2 IPS |
|
|
Object Detection (SP)
|
100% |
1222
97.0 IPS |
|
|
Object Detection (HP)
|
97% |
2285
181.9 IPS |
|
|
Object Detection (Q)
|
94% |
1681
134.0 IPS |
|
|
Face Detection (SP)
|
100% |
2568
30.5 IPS |
|
|
Face Detection (HP)
|
100% |
4779
56.8 IPS |
|
|
Face Detection (Q)
|
100% |
2713
32.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4743
36.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
9302
71.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
6513
50.9 IPS |
|
|
Style Transfer (SP)
|
100% |
12853
16.5 IPS |
|
|
Style Transfer (HP)
|
100% |
22464
28.9 IPS |
|
|
Style Transfer (Q)
|
96% |
19676
25.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2637
97.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4117
152.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3213
118.6 IPS |
|
|
Text Classification (SP)
|
99% |
4082
5.45 KIPS |
|
|
Text Classification (HP)
|
100% |
6453
8.61 KIPS |
|
|
Text Classification (Q)
|
93% |
6420
8.62 KIPS |
|
|
Machine Translation (SP)
|
100% |
2267
39.0 IPS |
|
|
Machine Translation (HP)
|
98% |
4120
71.2 IPS |
|
|
Machine Translation (Q)
|
98% |
4123
71.3 IPS |