| Upload Date | November 09 2025 04:02 PM |
| Views | 3 |
| 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% |
1348
250.7 IPS |
|
|
Image Classification (HP)
|
100% |
2053
381.7 IPS |
|
|
Image Classification (Q)
|
96% |
1478
276.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
649
10.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
904
14.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1044
16.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
1767
2.06 IPS |
|
|
Pose Estimation (HP)
|
100% |
4602
5.37 IPS |
|
|
Pose Estimation (Q)
|
95% |
3929
4.60 IPS |
|
|
Object Detection (SP)
|
100% |
502
39.8 IPS |
|
|
Object Detection (HP)
|
97% |
1175
93.6 IPS |
|
|
Object Detection (Q)
|
94% |
953
75.9 IPS |
|
|
Face Detection (SP)
|
100% |
1177
14.0 IPS |
|
|
Face Detection (HP)
|
100% |
1911
22.7 IPS |
|
|
Face Detection (Q)
|
100% |
1183
14.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
2976
22.9 IPS |
|
|
Depth Estimation (HP)
|
98% |
5536
42.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
2734
21.4 IPS |
|
|
Style Transfer (SP)
|
100% |
4695
6.04 IPS |
|
|
Style Transfer (HP)
|
100% |
7465
9.60 IPS |
|
|
Style Transfer (Q)
|
96% |
12448
16.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2813
103.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2281
84.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1661
61.3 IPS |
|
|
Text Classification (SP)
|
100% |
1957
2.61 KIPS |
|
|
Text Classification (HP)
|
99% |
2085
2.78 KIPS |
|
|
Text Classification (Q)
|
93% |
2233
3.00 KIPS |
|
|
Machine Translation (SP)
|
100% |
1093
18.8 IPS |
|
|
Machine Translation (HP)
|
98% |
1200
20.7 IPS |
|
|
Machine Translation (Q)
|
98% |
1119
19.3 IPS |