Upload Date | September 18 2025 08:57 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
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 | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2035
378.5 IPS |
|
Image Classification (HP)
|
100% |
15536
2.89 KIPS |
|
Image Classification (Q)
|
97% |
20743
3.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1901
30.8 IPS |
|
Image Segmentation (HP)
|
100% |
18196
295.0 IPS |
|
Image Segmentation (Q)
|
99% |
23777
385.4 IPS |
|
Pose Estimation (SP)
|
100% |
9233
10.8 IPS |
|
Pose Estimation (HP)
|
100% |
152817
178.3 IPS |
|
Pose Estimation (Q)
|
95% |
290931
341.0 IPS |
|
Object Detection (SP)
|
100% |
2320
184.0 IPS |
|
Object Detection (HP)
|
100% |
16141
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22614
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3820
45.4 IPS |
|
Face Detection (HP)
|
100% |
40143
477.0 IPS |
|
Face Detection (Q)
|
100% |
56210
667.9 IPS |
|
Depth Estimation (SP)
|
100% |
8270
63.7 IPS |
|
Depth Estimation (HP)
|
99% |
95104
732.7 IPS |
|
Depth Estimation (Q)
|
85% |
160785
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
20054
25.8 IPS |
|
Style Transfer (HP)
|
100% |
245149
315.1 IPS |
|
Style Transfer (Q)
|
96% |
303210
391.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5399
199.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
50711
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84249
3.11 KIPS |
|
Text Classification (SP)
|
100% |
3383
4.52 KIPS |
|
Text Classification (HP)
|
100% |
4668
6.23 KIPS |
|
Text Classification (Q)
|
93% |
4718
6.33 KIPS |
|
Machine Translation (SP)
|
100% |
4165
71.7 IPS |
|
Machine Translation (HP)
|
100% |
10028
172.7 IPS |
|
Machine Translation (Q)
|
98% |
11038
190.8 IPS |