| Upload Date | January 20 2026 11:56 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| 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% |
1329
247.1 IPS |
|
|
Image Classification (HP)
|
100% |
9249
1.72 KIPS |
|
|
Image Classification (Q)
|
97% |
10771
2.01 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1348
21.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
13785
223.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
19128
310.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
6192
7.23 IPS |
|
|
Pose Estimation (HP)
|
100% |
94872
110.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
100663
118.0 IPS |
|
|
Object Detection (SP)
|
100% |
1436
113.9 IPS |
|
|
Object Detection (HP)
|
100% |
11265
893.6 IPS |
|
|
Object Detection (Q)
|
91% |
13670
1.09 KIPS |
|
|
Face Detection (SP)
|
100% |
2997
35.6 IPS |
|
|
Face Detection (HP)
|
100% |
30610
363.7 IPS |
|
|
Face Detection (Q)
|
100% |
40100
476.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
5749
44.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
70740
545.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
89700
701.3 IPS |
|
|
Style Transfer (SP)
|
100% |
18019
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
169242
217.6 IPS |
|
|
Style Transfer (Q)
|
96% |
160851
207.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3757
138.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
32488
1.20 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
35700
1.32 KIPS |
|
|
Text Classification (SP)
|
100% |
2765
3.69 KIPS |
|
|
Text Classification (HP)
|
100% |
2575
3.44 KIPS |
|
|
Text Classification (Q)
|
93% |
2585
3.47 KIPS |
|
|
Machine Translation (SP)
|
100% |
3366
58.0 IPS |
|
|
Machine Translation (HP)
|
100% |
7189
123.8 IPS |
|
|
Machine Translation (Q)
|
98% |
8195
141.6 IPS |