Upload Date | September 01 2025 03:29 AM |
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% |
1692
314.6 IPS |
|
Image Classification (HP)
|
100% |
10906
2.03 KIPS |
|
Image Classification (Q)
|
97% |
15340
2.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1670
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
16420
266.2 IPS |
|
Image Segmentation (Q)
|
99% |
21417
347.2 IPS |
|
Pose Estimation (SP)
|
100% |
8170
9.53 IPS |
|
Pose Estimation (HP)
|
100% |
105794
123.4 IPS |
|
Pose Estimation (Q)
|
95% |
203884
239.0 IPS |
|
Object Detection (SP)
|
100% |
1779
141.1 IPS |
|
Object Detection (HP)
|
100% |
13788
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19227
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3111
37.0 IPS |
|
Face Detection (HP)
|
100% |
33824
401.9 IPS |
|
Face Detection (Q)
|
100% |
51462
611.5 IPS |
|
Depth Estimation (SP)
|
100% |
7094
54.7 IPS |
|
Depth Estimation (HP)
|
99% |
78315
603.4 IPS |
|
Depth Estimation (Q)
|
85% |
127404
996.1 IPS |
|
Style Transfer (SP)
|
100% |
21762
28.0 IPS |
|
Style Transfer (HP)
|
100% |
205960
264.8 IPS |
|
Style Transfer (Q)
|
96% |
254752
328.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4940
182.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
33673
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57956
2.14 KIPS |
|
Text Classification (SP)
|
100% |
3296
4.40 KIPS |
|
Text Classification (HP)
|
100% |
3274
4.37 KIPS |
|
Text Classification (Q)
|
93% |
3378
4.53 KIPS |
|
Machine Translation (SP)
|
100% |
3151
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6340
109.2 IPS |
|
Machine Translation (Q)
|
98% |
7338
126.8 IPS |