User | M91 |
Upload Date | April 06 2025 08:21 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
1194
222.0 IPS |
|
Image Classification (HP)
|
100% |
11891
2.21 KIPS |
|
Image Classification (Q)
|
97% |
15808
2.95 KIPS |
|
Image Segmentation (SP)
|
100% |
1193
19.3 IPS |
|
Image Segmentation (HP)
|
100% |
13175
213.6 IPS |
|
Image Segmentation (Q)
|
99% |
19948
323.4 IPS |
|
Pose Estimation (SP)
|
100% |
4233
4.94 IPS |
|
Pose Estimation (HP)
|
100% |
110399
128.8 IPS |
|
Pose Estimation (Q)
|
95% |
224674
263.3 IPS |
|
Object Detection (SP)
|
100% |
1574
124.8 IPS |
|
Object Detection (HP)
|
100% |
14335
1.14 KIPS |
|
Object Detection (Q)
|
91% |
18343
1.47 KIPS |
|
Face Detection (SP)
|
100% |
2652
31.5 IPS |
|
Face Detection (HP)
|
100% |
31319
372.1 IPS |
|
Face Detection (Q)
|
100% |
48460
575.8 IPS |
|
Depth Estimation (SP)
|
100% |
5381
41.5 IPS |
|
Depth Estimation (HP)
|
99% |
79372
611.5 IPS |
|
Depth Estimation (Q)
|
85% |
132107
1.03 KIPS |
|
Style Transfer (SP)
|
100% |
11458
14.7 IPS |
|
Style Transfer (HP)
|
100% |
189967
244.2 IPS |
|
Style Transfer (Q)
|
96% |
235946
304.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4002
147.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
37603
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
66402
2.45 KIPS |
|
Text Classification (SP)
|
100% |
2462
3.29 KIPS |
|
Text Classification (HP)
|
100% |
3770
5.03 KIPS |
|
Text Classification (Q)
|
93% |
4001
5.37 KIPS |
|
Machine Translation (SP)
|
100% |
3232
55.7 IPS |
|
Machine Translation (HP)
|
100% |
8736
150.5 IPS |
|
Machine Translation (Q)
|
98% |
9401
162.5 IPS |