| Upload Date | November 13 2025 11:33 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| 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 | 5.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1499
278.7 IPS |
|
|
Image Classification (HP)
|
100% |
1632
303.5 IPS |
|
|
Image Classification (Q)
|
96% |
1676
313.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
2871
46.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2926
47.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
2841
46.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
11848
13.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
12832
15.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
12698
14.9 IPS |
|
|
Object Detection (SP)
|
100% |
1883
149.3 IPS |
|
|
Object Detection (HP)
|
100% |
1962
155.6 IPS |
|
|
Object Detection (Q)
|
92% |
1743
139.1 IPS |
|
|
Face Detection (SP)
|
100% |
5289
62.8 IPS |
|
|
Face Detection (HP)
|
100% |
6273
74.5 IPS |
|
|
Face Detection (Q)
|
100% |
5136
61.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
8482
65.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
8820
68.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
8302
64.8 IPS |
|
|
Style Transfer (SP)
|
100% |
21299
27.4 IPS |
|
|
Style Transfer (HP)
|
100% |
24188
31.1 IPS |
|
|
Style Transfer (Q)
|
96% |
23640
30.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4820
178.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5010
185.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4272
157.7 IPS |
|
|
Text Classification (SP)
|
100% |
2823
3.77 KIPS |
|
|
Text Classification (HP)
|
99% |
4762
6.36 KIPS |
|
|
Text Classification (Q)
|
93% |
4813
6.46 KIPS |
|
|
Machine Translation (SP)
|
100% |
1063
18.3 IPS |
|
|
Machine Translation (HP)
|
100% |
1122
19.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1000
17.3 IPS |