User | PaulWSkierlo |
Upload Date | April 11 2025 05:45 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.4 |
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% |
2035
378.4 IPS |
|
Image Classification (HP)
|
100% |
15423
2.87 KIPS |
|
Image Classification (Q)
|
97% |
20425
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1802
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
18173
294.6 IPS |
|
Image Segmentation (Q)
|
99% |
23707
384.3 IPS |
|
Pose Estimation (SP)
|
100% |
9093
10.6 IPS |
|
Pose Estimation (HP)
|
100% |
153736
179.4 IPS |
|
Pose Estimation (Q)
|
95% |
292838
343.2 IPS |
|
Object Detection (SP)
|
100% |
2299
182.4 IPS |
|
Object Detection (HP)
|
100% |
16197
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22477
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3581
42.6 IPS |
|
Face Detection (HP)
|
100% |
39989
475.2 IPS |
|
Face Detection (Q)
|
100% |
56056
666.1 IPS |
|
Depth Estimation (SP)
|
100% |
8080
62.3 IPS |
|
Depth Estimation (HP)
|
99% |
94609
728.9 IPS |
|
Depth Estimation (Q)
|
85% |
158969
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
19150
24.6 IPS |
|
Style Transfer (HP)
|
100% |
244622
314.5 IPS |
|
Style Transfer (Q)
|
96% |
302925
390.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5450
201.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
50478
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84982
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3368
4.50 KIPS |
|
Text Classification (HP)
|
100% |
3528
4.71 KIPS |
|
Text Classification (Q)
|
93% |
2630
3.53 KIPS |
|
Machine Translation (SP)
|
100% |
3946
68.0 IPS |
|
Machine Translation (HP)
|
100% |
9830
169.3 IPS |
|
Machine Translation (Q)
|
98% |
10923
188.8 IPS |