| Upload Date | November 11 2025 04:41 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 16 Pro |
| Model ID | iPhone17,1 |
| Motherboard | D93AP |
| 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 | 7.46 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2075
385.8 IPS |
|
|
Image Classification (HP)
|
100% |
14916
2.77 KIPS |
|
|
Image Classification (Q)
|
97% |
18410
3.44 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1851
30.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
18079
293.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
23655
383.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
9083
10.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
152812
178.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
292670
343.0 IPS |
|
|
Object Detection (SP)
|
100% |
2345
186.0 IPS |
|
|
Object Detection (HP)
|
100% |
15703
1.25 KIPS |
|
|
Object Detection (Q)
|
91% |
21266
1.70 KIPS |
|
|
Face Detection (SP)
|
100% |
3728
44.3 IPS |
|
|
Face Detection (HP)
|
100% |
40425
480.3 IPS |
|
|
Face Detection (Q)
|
100% |
55447
658.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
8200
63.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
95920
739.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
154732
1.21 KIPS |
|
|
Style Transfer (SP)
|
100% |
22269
28.6 IPS |
|
|
Style Transfer (HP)
|
100% |
247144
317.7 IPS |
|
|
Style Transfer (Q)
|
96% |
296306
382.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5520
203.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
52667
1.94 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
80358
2.97 KIPS |
|
|
Text Classification (SP)
|
100% |
3706
4.95 KIPS |
|
|
Text Classification (HP)
|
99% |
6224
8.31 KIPS |
|
|
Text Classification (Q)
|
93% |
6122
8.22 KIPS |
|
|
Machine Translation (SP)
|
100% |
4196
72.3 IPS |
|
|
Machine Translation (HP)
|
100% |
9404
162.0 IPS |
|
|
Machine Translation (Q)
|
98% |
10372
179.2 IPS |