| Upload Date | January 21 2026 09:13 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| 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% |
865
160.8 IPS |
|
|
Image Classification (HP)
|
100% |
1651
307.1 IPS |
|
|
Image Classification (Q)
|
96% |
1088
203.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
892
14.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1496
24.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
1716
27.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4247
4.96 IPS |
|
|
Pose Estimation (HP)
|
100% |
9184
10.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
8117
9.51 IPS |
|
|
Object Detection (SP)
|
100% |
864
68.6 IPS |
|
|
Object Detection (HP)
|
97% |
1888
150.3 IPS |
|
|
Object Detection (Q)
|
94% |
1334
106.3 IPS |
|
|
Face Detection (SP)
|
100% |
1851
22.0 IPS |
|
|
Face Detection (HP)
|
100% |
3717
44.2 IPS |
|
|
Face Detection (Q)
|
100% |
2097
24.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
3866
29.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
7114
55.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
5113
40.0 IPS |
|
|
Style Transfer (SP)
|
100% |
11485
14.8 IPS |
|
|
Style Transfer (HP)
|
100% |
18224
23.4 IPS |
|
|
Style Transfer (Q)
|
96% |
15428
19.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2483
91.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3328
122.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2492
92.0 IPS |
|
|
Text Classification (SP)
|
100% |
1967
2.63 KIPS |
|
|
Text Classification (HP)
|
99% |
3274
4.37 KIPS |
|
|
Text Classification (Q)
|
93% |
3246
4.36 KIPS |
|
|
Machine Translation (SP)
|
100% |
1522
26.2 IPS |
|
|
Machine Translation (HP)
|
98% |
4000
69.1 IPS |
|
|
Machine Translation (Q)
|
98% |
4209
72.7 IPS |