User | balazskake |
Upload Date | September 22 2025 07:00 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0 |
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% |
536
99.6 IPS |
|
Image Classification (HP)
|
100% |
2681
498.5 IPS |
|
Image Classification (Q)
|
96% |
2746
512.8 IPS |
|
Image Segmentation (SP)
|
100% |
621
10.1 IPS |
|
Image Segmentation (HP)
|
100% |
4444
72.0 IPS |
|
Image Segmentation (Q)
|
99% |
4683
75.9 IPS |
|
Pose Estimation (SP)
|
100% |
2502
2.92 IPS |
|
Pose Estimation (HP)
|
100% |
33212
38.8 IPS |
|
Pose Estimation (Q)
|
95% |
32734
38.4 IPS |
|
Object Detection (SP)
|
100% |
545
43.2 IPS |
|
Object Detection (HP)
|
99% |
3279
260.8 IPS |
|
Object Detection (Q)
|
91% |
2959
236.4 IPS |
|
Face Detection (SP)
|
100% |
1354
16.1 IPS |
|
Face Detection (HP)
|
100% |
6341
75.3 IPS |
|
Face Detection (Q)
|
100% |
6149
73.1 IPS |
|
Depth Estimation (SP)
|
100% |
2146
16.5 IPS |
|
Depth Estimation (HP)
|
99% |
22465
173.1 IPS |
|
Depth Estimation (Q)
|
85% |
22212
173.6 IPS |
|
Style Transfer (SP)
|
100% |
6891
8.86 IPS |
|
Style Transfer (HP)
|
100% |
59694
76.7 IPS |
|
Style Transfer (Q)
|
96% |
57822
74.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1474
54.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
12010
443.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
12219
451.2 IPS |
|
Text Classification (SP)
|
100% |
1097
1.46 KIPS |
|
Text Classification (HP)
|
100% |
1906
2.54 KIPS |
|
Text Classification (Q)
|
93% |
1942
2.61 KIPS |
|
Machine Translation (SP)
|
100% |
1208
20.8 IPS |
|
Machine Translation (HP)
|
100% |
3286
56.6 IPS |
|
Machine Translation (Q)
|
98% |
3463
59.9 IPS |