| Upload Date | January 20 2026 11:46 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 12 Mini |
| Model ID | iPhone13,1 |
| Motherboard | D52gAP |
| 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 | 3.61 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1207
224.5 IPS |
|
|
Image Classification (HP)
|
100% |
2047
380.6 IPS |
|
|
Image Classification (Q)
|
96% |
1448
270.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1116
18.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1734
28.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
2145
34.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4856
5.67 IPS |
|
|
Pose Estimation (HP)
|
100% |
10642
12.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
9469
11.1 IPS |
|
|
Object Detection (SP)
|
100% |
1186
94.1 IPS |
|
|
Object Detection (HP)
|
97% |
2247
178.9 IPS |
|
|
Object Detection (Q)
|
94% |
1644
131.0 IPS |
|
|
Face Detection (SP)
|
100% |
2503
29.7 IPS |
|
|
Face Detection (HP)
|
100% |
4656
55.3 IPS |
|
|
Face Detection (Q)
|
100% |
2695
32.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
4685
36.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
9275
71.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
6565
51.3 IPS |
|
|
Style Transfer (SP)
|
100% |
12973
16.7 IPS |
|
|
Style Transfer (HP)
|
100% |
22425
28.8 IPS |
|
|
Style Transfer (Q)
|
96% |
19513
25.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2707
99.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4132
152.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3210
118.5 IPS |
|
|
Text Classification (SP)
|
100% |
2291
3.06 KIPS |
|
|
Text Classification (HP)
|
99% |
3843
5.13 KIPS |
|
|
Text Classification (Q)
|
93% |
3842
5.16 KIPS |
|
|
Machine Translation (SP)
|
100% |
2253
38.8 IPS |
|
|
Machine Translation (HP)
|
98% |
4212
72.8 IPS |
|
|
Machine Translation (Q)
|
98% |
4242
73.3 IPS |