Upload Date | September 13 2025 07:09 PM |
Views | 4 |
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% |
2066
384.3 IPS |
|
Image Classification (HP)
|
100% |
15210
2.83 KIPS |
|
Image Classification (Q)
|
97% |
19474
3.63 KIPS |
|
Image Segmentation (SP)
|
100% |
1959
31.8 IPS |
|
Image Segmentation (HP)
|
100% |
18244
295.8 IPS |
|
Image Segmentation (Q)
|
99% |
24027
389.5 IPS |
|
Pose Estimation (SP)
|
100% |
9453
11.0 IPS |
|
Pose Estimation (HP)
|
100% |
153764
179.4 IPS |
|
Pose Estimation (Q)
|
95% |
292362
342.7 IPS |
|
Object Detection (SP)
|
100% |
2344
185.9 IPS |
|
Object Detection (HP)
|
100% |
16631
1.32 KIPS |
|
Object Detection (Q)
|
91% |
22676
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3868
46.0 IPS |
|
Face Detection (HP)
|
100% |
40983
487.0 IPS |
|
Face Detection (Q)
|
100% |
57585
684.2 IPS |
|
Depth Estimation (SP)
|
100% |
8272
63.7 IPS |
|
Depth Estimation (HP)
|
99% |
95276
734.0 IPS |
|
Depth Estimation (Q)
|
85% |
161995
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
20356
26.2 IPS |
|
Style Transfer (HP)
|
100% |
246283
316.6 IPS |
|
Style Transfer (Q)
|
96% |
304722
393.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5312
196.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
50345
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84691
3.13 KIPS |
|
Text Classification (SP)
|
100% |
3411
4.55 KIPS |
|
Text Classification (HP)
|
100% |
4983
6.65 KIPS |
|
Text Classification (Q)
|
93% |
5001
6.71 KIPS |
|
Machine Translation (SP)
|
100% |
4183
72.0 IPS |
|
Machine Translation (HP)
|
100% |
10250
176.6 IPS |
|
Machine Translation (Q)
|
98% |
11422
197.4 IPS |