User | Farzad |
Upload Date | February 19 2025 10:11 PM |
Views | 13 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.3.1 |
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% |
1970
366.3 IPS |
|
Image Classification (HP)
|
100% |
15185
2.82 KIPS |
|
Image Classification (Q)
|
97% |
20100
3.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1902
30.8 IPS |
|
Image Segmentation (HP)
|
100% |
18262
296.0 IPS |
|
Image Segmentation (Q)
|
99% |
23970
388.6 IPS |
|
Pose Estimation (SP)
|
100% |
8097
9.45 IPS |
|
Pose Estimation (HP)
|
100% |
147167
171.7 IPS |
|
Pose Estimation (Q)
|
95% |
292303
342.6 IPS |
|
Object Detection (SP)
|
100% |
2076
164.7 IPS |
|
Object Detection (HP)
|
100% |
16233
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22162
1.77 KIPS |
|
Face Detection (SP)
|
100% |
3459
41.1 IPS |
|
Face Detection (HP)
|
100% |
41179
489.3 IPS |
|
Face Detection (Q)
|
100% |
57608
684.5 IPS |
|
Depth Estimation (SP)
|
100% |
7405
57.0 IPS |
|
Depth Estimation (HP)
|
99% |
94754
730.0 IPS |
|
Depth Estimation (Q)
|
85% |
159673
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
22352
28.7 IPS |
|
Style Transfer (HP)
|
100% |
244945
314.9 IPS |
|
Style Transfer (Q)
|
96% |
305831
394.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5332
196.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
49246
1.82 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83117
3.07 KIPS |
|
Text Classification (SP)
|
100% |
3412
4.55 KIPS |
|
Text Classification (HP)
|
100% |
3300
4.40 KIPS |
|
Text Classification (Q)
|
93% |
3027
4.06 KIPS |
|
Machine Translation (SP)
|
100% |
3734
64.3 IPS |
|
Machine Translation (HP)
|
100% |
9407
162.0 IPS |
|
Machine Translation (Q)
|
98% |
11229
194.0 IPS |