Upload Date | October 13 2025 11:52 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0.1 |
Model | iPhone 13 Pro Max |
Model ID | iPhone14,3 |
Motherboard | D64AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1261
234.5 IPS |
|
Image Classification (HP)
|
100% |
7182
1.34 KIPS |
|
Image Classification (Q)
|
96% |
9586
1.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1242
20.1 IPS |
|
Image Segmentation (HP)
|
100% |
13302
215.6 IPS |
|
Image Segmentation (Q)
|
99% |
13578
220.1 IPS |
|
Pose Estimation (SP)
|
100% |
5664
6.61 IPS |
|
Pose Estimation (HP)
|
100% |
81083
94.6 IPS |
|
Pose Estimation (Q)
|
95% |
86669
101.6 IPS |
|
Object Detection (SP)
|
100% |
1349
107.0 IPS |
|
Object Detection (HP)
|
99% |
10180
809.8 IPS |
|
Object Detection (Q)
|
91% |
11924
952.8 IPS |
|
Face Detection (SP)
|
100% |
2618
31.1 IPS |
|
Face Detection (HP)
|
100% |
22883
271.9 IPS |
|
Face Detection (Q)
|
100% |
36504
433.7 IPS |
|
Depth Estimation (SP)
|
100% |
5167
39.8 IPS |
|
Depth Estimation (HP)
|
99% |
52947
407.9 IPS |
|
Depth Estimation (Q)
|
85% |
64943
507.5 IPS |
|
Style Transfer (SP)
|
100% |
16941
21.8 IPS |
|
Style Transfer (HP)
|
100% |
148763
191.2 IPS |
|
Style Transfer (Q)
|
96% |
136451
176.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3648
134.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
27121
1.00 KIPS |
|
Image Super-Resolution (Q)
|
99% |
27452
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2577
3.44 KIPS |
|
Text Classification (HP)
|
100% |
1522
2.03 KIPS |
|
Text Classification (Q)
|
93% |
2138
2.87 KIPS |
|
Machine Translation (SP)
|
100% |
3496
60.2 IPS |
|
Machine Translation (HP)
|
100% |
6102
105.1 IPS |
|
Machine Translation (Q)
|
98% |
6843
118.3 IPS |