| Upload Date | November 22 2025 07:33 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
1161
215.9 IPS |
|
|
Image Classification (HP)
|
100% |
2022
376.1 IPS |
|
|
Image Classification (Q)
|
96% |
1440
268.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
861
14.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1379
22.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
1940
31.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
3430
4.00 IPS |
|
|
Pose Estimation (HP)
|
100% |
7902
9.22 IPS |
|
|
Pose Estimation (Q)
|
95% |
6763
7.93 IPS |
|
|
Object Detection (SP)
|
100% |
858
68.1 IPS |
|
|
Object Detection (HP)
|
97% |
1585
126.2 IPS |
|
|
Object Detection (Q)
|
94% |
1161
92.5 IPS |
|
|
Face Detection (SP)
|
100% |
1915
22.8 IPS |
|
|
Face Detection (HP)
|
100% |
3613
42.9 IPS |
|
|
Face Detection (Q)
|
100% |
2046
24.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
3147
24.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
6289
48.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
4503
35.2 IPS |
|
|
Style Transfer (SP)
|
100% |
9123
11.7 IPS |
|
|
Style Transfer (HP)
|
100% |
14819
19.0 IPS |
|
|
Style Transfer (Q)
|
96% |
13275
17.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2064
76.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3123
115.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2226
82.2 IPS |
|
|
Text Classification (SP)
|
100% |
2221
2.96 KIPS |
|
|
Text Classification (HP)
|
99% |
3751
5.01 KIPS |
|
|
Text Classification (Q)
|
93% |
3733
5.01 KIPS |
|
|
Machine Translation (SP)
|
100% |
1603
27.6 IPS |
|
|
Machine Translation (HP)
|
98% |
3203
55.3 IPS |
|
|
Machine Translation (Q)
|
98% |
3311
57.2 IPS |