| Upload Date | November 15 2025 03:11 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 14 Pro |
| Model ID | iPhone15,2 |
| Motherboard | D73AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.53 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1670
310.5 IPS |
|
|
Image Classification (HP)
|
100% |
1644
305.7 IPS |
|
|
Image Classification (Q)
|
96% |
1645
307.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
2867
46.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2896
46.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2806
45.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
11790
13.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
12888
15.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
12484
14.6 IPS |
|
|
Object Detection (SP)
|
100% |
1930
153.1 IPS |
|
|
Object Detection (HP)
|
100% |
1952
154.8 IPS |
|
|
Object Detection (Q)
|
92% |
1763
140.7 IPS |
|
|
Face Detection (SP)
|
100% |
5571
66.2 IPS |
|
|
Face Detection (HP)
|
100% |
5820
69.2 IPS |
|
|
Face Detection (Q)
|
100% |
5047
60.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
8652
66.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
8997
69.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
8479
66.2 IPS |
|
|
Style Transfer (SP)
|
100% |
20942
26.9 IPS |
|
|
Style Transfer (HP)
|
100% |
24185
31.1 IPS |
|
|
Style Transfer (Q)
|
96% |
23519
30.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4924
181.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5204
192.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4654
171.8 IPS |
|
|
Text Classification (SP)
|
100% |
2788
3.72 KIPS |
|
|
Text Classification (HP)
|
99% |
4745
6.33 KIPS |
|
|
Text Classification (Q)
|
93% |
4714
6.33 KIPS |
|
|
Machine Translation (SP)
|
100% |
1172
20.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1012
17.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1019
17.6 IPS |