| Upload Date | November 06 2025 06:32 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone 15 Pro Max |
| Model ID | iPhone16,2 |
| Motherboard | D84AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1546
287.5 IPS |
|
|
Image Classification (HP)
|
100% |
2942
547.1 IPS |
|
|
Image Classification (Q)
|
96% |
2034
379.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1511
24.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2321
37.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
3014
48.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
7326
8.55 IPS |
|
|
Pose Estimation (HP)
|
100% |
16046
18.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
13825
16.2 IPS |
|
|
Object Detection (SP)
|
100% |
1635
129.7 IPS |
|
|
Object Detection (HP)
|
97% |
3228
257.0 IPS |
|
|
Object Detection (Q)
|
94% |
2328
185.6 IPS |
|
|
Face Detection (SP)
|
100% |
2975
35.4 IPS |
|
|
Face Detection (HP)
|
100% |
6590
78.3 IPS |
|
|
Face Detection (Q)
|
100% |
3724
44.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
6541
50.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
12591
97.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
8819
68.9 IPS |
|
|
Style Transfer (SP)
|
100% |
20201
26.0 IPS |
|
|
Style Transfer (HP)
|
100% |
32401
41.7 IPS |
|
|
Style Transfer (Q)
|
96% |
26878
34.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4472
165.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5661
209.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4324
159.7 IPS |
|
|
Text Classification (SP)
|
100% |
3253
4.34 KIPS |
|
|
Text Classification (HP)
|
99% |
5479
7.31 KIPS |
|
|
Text Classification (Q)
|
93% |
5397
7.24 KIPS |
|
|
Machine Translation (SP)
|
100% |
3064
52.8 IPS |
|
|
Machine Translation (HP)
|
98% |
7154
123.6 IPS |
|
|
Machine Translation (Q)
|
98% |
7195
124.3 IPS |