Upload Date | September 02 2025 04:32 AM |
Views | 1 |
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% |
1629
303.0 IPS |
|
Image Classification (HP)
|
100% |
11130
2.07 KIPS |
|
Image Classification (Q)
|
97% |
14756
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1601
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
16244
263.3 IPS |
|
Image Segmentation (Q)
|
99% |
21217
343.9 IPS |
|
Pose Estimation (SP)
|
100% |
7694
8.98 IPS |
|
Pose Estimation (HP)
|
100% |
105355
122.9 IPS |
|
Pose Estimation (Q)
|
95% |
204763
240.0 IPS |
|
Object Detection (SP)
|
100% |
1764
139.9 IPS |
|
Object Detection (HP)
|
100% |
14059
1.12 KIPS |
|
Object Detection (Q)
|
91% |
18965
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3075
36.5 IPS |
|
Face Detection (HP)
|
100% |
33620
399.5 IPS |
|
Face Detection (Q)
|
100% |
53083
630.7 IPS |
|
Depth Estimation (SP)
|
100% |
6972
53.7 IPS |
|
Depth Estimation (HP)
|
99% |
78390
603.9 IPS |
|
Depth Estimation (Q)
|
85% |
130413
1.02 KIPS |
|
Style Transfer (SP)
|
100% |
21079
27.1 IPS |
|
Style Transfer (HP)
|
100% |
209751
269.6 IPS |
|
Style Transfer (Q)
|
96% |
250286
323.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4817
177.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34175
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54674
2.02 KIPS |
|
Text Classification (SP)
|
100% |
3284
4.38 KIPS |
|
Text Classification (HP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (Q)
|
93% |
2177
2.92 KIPS |
|
Machine Translation (SP)
|
100% |
3152
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6386
110.0 IPS |
|
Machine Translation (Q)
|
98% |
7491
129.4 IPS |