User | Ggallyup |
Upload Date | June 11 2025 12:59 AM |
Views | 8 |
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% |
2020
375.6 IPS |
|
Image Classification (HP)
|
100% |
15109
2.81 KIPS |
|
Image Classification (Q)
|
97% |
20145
3.76 KIPS |
|
Image Segmentation (SP)
|
100% |
1823
29.6 IPS |
|
Image Segmentation (HP)
|
100% |
18173
294.6 IPS |
|
Image Segmentation (Q)
|
99% |
23739
384.8 IPS |
|
Pose Estimation (SP)
|
100% |
8966
10.5 IPS |
|
Pose Estimation (HP)
|
100% |
153766
179.4 IPS |
|
Pose Estimation (Q)
|
95% |
293697
344.2 IPS |
|
Object Detection (SP)
|
100% |
2292
181.8 IPS |
|
Object Detection (HP)
|
100% |
16308
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22687
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3603
42.8 IPS |
|
Face Detection (HP)
|
100% |
40289
478.7 IPS |
|
Face Detection (Q)
|
100% |
56875
675.8 IPS |
|
Depth Estimation (SP)
|
100% |
8125
62.6 IPS |
|
Depth Estimation (HP)
|
99% |
95356
734.7 IPS |
|
Depth Estimation (Q)
|
85% |
159544
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
19038
24.5 IPS |
|
Style Transfer (HP)
|
100% |
245758
315.9 IPS |
|
Style Transfer (Q)
|
96% |
303298
391.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5370
198.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
50921
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84921
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3385
4.52 KIPS |
|
Text Classification (HP)
|
100% |
4736
6.32 KIPS |
|
Text Classification (Q)
|
93% |
5031
6.75 KIPS |
|
Machine Translation (SP)
|
100% |
3916
67.4 IPS |
|
Machine Translation (HP)
|
100% |
10321
177.8 IPS |
|
Machine Translation (Q)
|
98% |
11375
196.6 IPS |