| Upload Date | November 20 2026 04:06 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A18 |
| System Information | |
|---|---|
| Operating System | iOS 27.3 |
| 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 | 7.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1056
196.4 IPS |
|
|
Image Classification (HP)
|
100% |
851
158.2 IPS |
|
|
Image Classification (Q)
|
97% |
832
155.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
4350
70.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
4627
75.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
4501
73.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
13146
15.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
13598
15.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
13638
16.0 IPS |
|
|
Object Detection (SP)
|
100% |
1612
127.9 IPS |
|
|
Object Detection (HP)
|
100% |
1536
121.9 IPS |
|
|
Object Detection (Q)
|
89% |
3200
256.3 IPS |
|
|
Face Detection (SP)
|
100% |
8396
99.8 IPS |
|
|
Face Detection (HP)
|
100% |
10372
123.2 IPS |
|
|
Face Detection (Q)
|
100% |
6950
82.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
10070
77.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
12313
94.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
11071
86.5 IPS |
|
|
Style Transfer (SP)
|
100% |
25292
32.5 IPS |
|
|
Style Transfer (HP)
|
100% |
34249
44.0 IPS |
|
|
Style Transfer (Q)
|
96% |
33002
42.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6301
232.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6268
231.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5583
206.2 IPS |
|
|
Text Classification (SP)
|
100% |
7092
9.47 KIPS |
|
|
Text Classification (HP)
|
99% |
11302
15.1 KIPS |
|
|
Text Classification (Q)
|
93% |
11106
14.9 KIPS |
|
|
Machine Translation (SP)
|
100% |
1000
17.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1380
23.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1168
20.2 IPS |