User | TILR |
Upload Date | September 25 2025 02:05 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 |
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
228.8 IPS |
|
Image Classification (HP)
|
100% |
4719
877.6 IPS |
|
Image Classification (Q)
|
96% |
4953
925.0 IPS |
|
Image Segmentation (SP)
|
100% |
1124
18.2 IPS |
|
Image Segmentation (HP)
|
100% |
7985
129.4 IPS |
|
Image Segmentation (Q)
|
99% |
8542
138.5 IPS |
|
Pose Estimation (SP)
|
100% |
4738
5.53 IPS |
|
Pose Estimation (HP)
|
100% |
61543
71.8 IPS |
|
Pose Estimation (Q)
|
95% |
60483
70.9 IPS |
|
Object Detection (SP)
|
100% |
1196
94.9 IPS |
|
Object Detection (HP)
|
99% |
5720
455.0 IPS |
|
Object Detection (Q)
|
91% |
5155
411.9 IPS |
|
Face Detection (SP)
|
100% |
2508
29.8 IPS |
|
Face Detection (HP)
|
100% |
11958
142.1 IPS |
|
Face Detection (Q)
|
100% |
10633
126.3 IPS |
|
Depth Estimation (SP)
|
100% |
4535
34.9 IPS |
|
Depth Estimation (HP)
|
99% |
35981
277.2 IPS |
|
Depth Estimation (Q)
|
85% |
36763
287.3 IPS |
|
Style Transfer (SP)
|
100% |
12917
16.6 IPS |
|
Style Transfer (HP)
|
100% |
104157
133.9 IPS |
|
Style Transfer (Q)
|
96% |
95357
123.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2674
98.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
17648
651.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
18667
689.3 IPS |
|
Text Classification (SP)
|
100% |
2316
3.09 KIPS |
|
Text Classification (HP)
|
100% |
2342
3.13 KIPS |
|
Text Classification (Q)
|
93% |
2496
3.35 KIPS |
|
Machine Translation (SP)
|
100% |
2252
38.8 IPS |
|
Machine Translation (HP)
|
100% |
3584
61.7 IPS |
|
Machine Translation (Q)
|
98% |
4147
71.7 IPS |