| Upload Date | November 20 2026 02:11 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.7.3 |
| Model | iPhone 11 Pro Max |
| Model ID | iPhone12,5 |
| Motherboard | D431AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.66 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
803
149.3 IPS |
|
|
Image Classification (HP)
|
100% |
1332
247.7 IPS |
|
|
Image Classification (Q)
|
96% |
967
180.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
855
13.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
1258
20.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
1467
23.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
3622
4.23 IPS |
|
|
Pose Estimation (HP)
|
100% |
6642
7.75 IPS |
|
|
Pose Estimation (Q)
|
95% |
5919
6.94 IPS |
|
|
Object Detection (SP)
|
100% |
793
62.9 IPS |
|
|
Object Detection (HP)
|
97% |
1621
129.0 IPS |
|
|
Object Detection (Q)
|
94% |
1177
93.8 IPS |
|
|
Face Detection (SP)
|
100% |
1680
20.0 IPS |
|
|
Face Detection (HP)
|
100% |
3241
38.5 IPS |
|
|
Face Detection (Q)
|
100% |
1869
22.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
3161
24.4 IPS |
|
|
Depth Estimation (HP)
|
97% |
5922
45.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
4350
34.0 IPS |
|
|
Style Transfer (SP)
|
100% |
7769
9.99 IPS |
|
|
Style Transfer (HP)
|
100% |
14467
18.6 IPS |
|
|
Style Transfer (Q)
|
96% |
12326
15.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2025
74.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2778
102.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2193
81.0 IPS |
|
|
Text Classification (SP)
|
99% |
2248
3.00 KIPS |
|
|
Text Classification (HP)
|
99% |
3819
5.10 KIPS |
|
|
Text Classification (Q)
|
93% |
3807
5.11 KIPS |
|
|
Machine Translation (SP)
|
100% |
1152
19.8 IPS |
|
|
Machine Translation (HP)
|
98% |
2750
47.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2488
43.0 IPS |