User | Fabianlozano |
Upload Date | August 09 2025 01:37 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1667
310.1 IPS |
|
Image Classification (HP)
|
100% |
11209
2.08 KIPS |
|
Image Classification (Q)
|
97% |
15492
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1651
26.8 IPS |
|
Image Segmentation (HP)
|
100% |
16668
270.2 IPS |
|
Image Segmentation (Q)
|
99% |
21094
341.9 IPS |
|
Pose Estimation (SP)
|
100% |
8512
9.93 IPS |
|
Pose Estimation (HP)
|
100% |
107176
125.1 IPS |
|
Pose Estimation (Q)
|
95% |
205818
241.2 IPS |
|
Object Detection (SP)
|
100% |
1761
139.7 IPS |
|
Object Detection (HP)
|
100% |
13875
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18107
1.45 KIPS |
|
Face Detection (SP)
|
100% |
3177
37.7 IPS |
|
Face Detection (HP)
|
100% |
33702
400.5 IPS |
|
Face Detection (Q)
|
100% |
47484
564.2 IPS |
|
Depth Estimation (SP)
|
100% |
7143
55.0 IPS |
|
Depth Estimation (HP)
|
99% |
78558
605.2 IPS |
|
Depth Estimation (Q)
|
85% |
123120
962.6 IPS |
|
Style Transfer (SP)
|
100% |
22053
28.3 IPS |
|
Style Transfer (HP)
|
100% |
206886
266.0 IPS |
|
Style Transfer (Q)
|
96% |
246655
318.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5010
185.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
34342
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55241
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3210
4.28 KIPS |
|
Text Classification (HP)
|
99% |
5520
7.37 KIPS |
|
Text Classification (Q)
|
93% |
5703
7.65 KIPS |
|
Machine Translation (SP)
|
100% |
3162
54.5 IPS |
|
Machine Translation (HP)
|
100% |
8345
143.7 IPS |
|
Machine Translation (Q)
|
98% |
9289
160.5 IPS |