User | MidniteMarv |
Upload Date | May 31 2025 11:26 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPhone 16 |
Model ID | iPhone17,3 |
Motherboard | D47AP |
CPU Information | |
---|---|
Name | Apple A18 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2011
373.9 IPS |
|
Image Classification (HP)
|
100% |
15386
2.86 KIPS |
|
Image Classification (Q)
|
97% |
21014
3.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1789
29.0 IPS |
|
Image Segmentation (HP)
|
100% |
18174
294.6 IPS |
|
Image Segmentation (Q)
|
99% |
23796
385.8 IPS |
|
Pose Estimation (SP)
|
100% |
8549
9.97 IPS |
|
Pose Estimation (HP)
|
100% |
152748
178.2 IPS |
|
Pose Estimation (Q)
|
95% |
292912
343.3 IPS |
|
Object Detection (SP)
|
100% |
2264
179.6 IPS |
|
Object Detection (HP)
|
100% |
16275
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22764
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3557
42.3 IPS |
|
Face Detection (HP)
|
100% |
40601
482.4 IPS |
|
Face Detection (Q)
|
100% |
56638
673.0 IPS |
|
Depth Estimation (SP)
|
100% |
7976
61.5 IPS |
|
Depth Estimation (HP)
|
99% |
96115
740.5 IPS |
|
Depth Estimation (Q)
|
85% |
160646
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
18275
23.5 IPS |
|
Style Transfer (HP)
|
100% |
245293
315.3 IPS |
|
Style Transfer (Q)
|
96% |
304010
392.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5150
190.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
50359
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84484
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3377
4.51 KIPS |
|
Text Classification (HP)
|
100% |
4936
6.59 KIPS |
|
Text Classification (Q)
|
93% |
4908
6.59 KIPS |
|
Machine Translation (SP)
|
100% |
3949
68.0 IPS |
|
Machine Translation (HP)
|
100% |
10295
177.3 IPS |
|
Machine Translation (Q)
|
98% |
11655
201.4 IPS |