User | iPhonedo |
Upload Date | March 03 2025 03:01 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
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% |
2069
384.8 IPS |
|
Image Classification (HP)
|
100% |
15199
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20741
3.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1912
31.0 IPS |
|
Image Segmentation (HP)
|
100% |
18176
294.6 IPS |
|
Image Segmentation (Q)
|
99% |
23929
387.9 IPS |
|
Pose Estimation (SP)
|
100% |
8927
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
152334
177.7 IPS |
|
Pose Estimation (Q)
|
95% |
292985
343.4 IPS |
|
Object Detection (SP)
|
100% |
2321
184.1 IPS |
|
Object Detection (HP)
|
100% |
16123
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22335
1.78 KIPS |
|
Face Detection (SP)
|
100% |
3868
46.0 IPS |
|
Face Detection (HP)
|
100% |
40925
486.3 IPS |
|
Face Detection (Q)
|
100% |
59038
701.5 IPS |
|
Depth Estimation (SP)
|
100% |
8162
62.9 IPS |
|
Depth Estimation (HP)
|
99% |
94697
729.6 IPS |
|
Depth Estimation (Q)
|
85% |
160555
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
20524
26.4 IPS |
|
Style Transfer (HP)
|
100% |
245415
315.5 IPS |
|
Style Transfer (Q)
|
96% |
304547
393.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5337
197.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
51053
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85681
3.16 KIPS |
|
Text Classification (SP)
|
100% |
3392
4.53 KIPS |
|
Text Classification (HP)
|
100% |
4366
5.83 KIPS |
|
Text Classification (Q)
|
93% |
4334
5.82 KIPS |
|
Machine Translation (SP)
|
100% |
4137
71.3 IPS |
|
Machine Translation (HP)
|
100% |
10006
172.4 IPS |
|
Machine Translation (Q)
|
98% |
10707
185.0 IPS |