Upload Date | September 18 2025 05:00 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2027
377.0 IPS |
|
Image Classification (HP)
|
100% |
14706
2.73 KIPS |
|
Image Classification (Q)
|
97% |
18818
3.51 KIPS |
|
Image Segmentation (SP)
|
100% |
1791
29.0 IPS |
|
Image Segmentation (HP)
|
100% |
18128
293.9 IPS |
|
Image Segmentation (Q)
|
99% |
23533
381.5 IPS |
|
Pose Estimation (SP)
|
100% |
8521
9.94 IPS |
|
Pose Estimation (HP)
|
100% |
147453
172.1 IPS |
|
Pose Estimation (Q)
|
95% |
289006
338.7 IPS |
|
Object Detection (SP)
|
100% |
2259
179.2 IPS |
|
Object Detection (HP)
|
100% |
15557
1.23 KIPS |
|
Object Detection (Q)
|
91% |
21353
1.71 KIPS |
|
Face Detection (SP)
|
100% |
3494
41.5 IPS |
|
Face Detection (HP)
|
100% |
39582
470.3 IPS |
|
Face Detection (Q)
|
100% |
53122
631.2 IPS |
|
Depth Estimation (SP)
|
100% |
7935
61.1 IPS |
|
Depth Estimation (HP)
|
99% |
93903
723.5 IPS |
|
Depth Estimation (Q)
|
85% |
157962
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
20770
26.7 IPS |
|
Style Transfer (HP)
|
100% |
244103
313.8 IPS |
|
Style Transfer (Q)
|
96% |
295868
381.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5309
196.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
51289
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79575
2.94 KIPS |
|
Text Classification (SP)
|
100% |
3719
4.96 KIPS |
|
Text Classification (HP)
|
99% |
6142
8.20 KIPS |
|
Text Classification (Q)
|
93% |
6140
8.24 KIPS |
|
Machine Translation (SP)
|
100% |
4050
69.8 IPS |
|
Machine Translation (HP)
|
100% |
9083
156.5 IPS |
|
Machine Translation (Q)
|
98% |
10150
175.4 IPS |