Upload Date | September 19 2025 06:09 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1689
314.2 IPS |
|
Image Classification (HP)
|
100% |
11488
2.14 KIPS |
|
Image Classification (Q)
|
97% |
15854
2.96 KIPS |
|
Image Segmentation (SP)
|
100% |
1598
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
16587
268.9 IPS |
|
Image Segmentation (Q)
|
99% |
21390
346.7 IPS |
|
Pose Estimation (SP)
|
100% |
7719
9.01 IPS |
|
Pose Estimation (HP)
|
100% |
105820
123.5 IPS |
|
Pose Estimation (Q)
|
95% |
205372
240.7 IPS |
|
Object Detection (SP)
|
100% |
1783
141.4 IPS |
|
Object Detection (HP)
|
100% |
13696
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19580
1.56 KIPS |
|
Face Detection (SP)
|
100% |
3117
37.0 IPS |
|
Face Detection (HP)
|
100% |
36514
433.9 IPS |
|
Face Detection (Q)
|
100% |
51457
611.4 IPS |
|
Depth Estimation (SP)
|
100% |
6930
53.4 IPS |
|
Depth Estimation (HP)
|
99% |
78796
607.1 IPS |
|
Depth Estimation (Q)
|
85% |
127749
998.8 IPS |
|
Style Transfer (SP)
|
100% |
20979
27.0 IPS |
|
Style Transfer (HP)
|
100% |
205968
264.8 IPS |
|
Style Transfer (Q)
|
96% |
255760
330.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4800
177.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34272
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
64814
2.39 KIPS |
|
Text Classification (SP)
|
100% |
3284
4.38 KIPS |
|
Text Classification (HP)
|
100% |
3286
4.39 KIPS |
|
Text Classification (Q)
|
93% |
3482
4.67 KIPS |
|
Machine Translation (SP)
|
100% |
3115
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6762
116.5 IPS |
|
Machine Translation (Q)
|
98% |
7560
130.6 IPS |