| Upload Date | December 03 2025 08:45 PM |
| Views | 9 |
| 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% |
1535
285.5 IPS |
|
|
Image Classification (HP)
|
100% |
2957
549.9 IPS |
|
|
Image Classification (Q)
|
96% |
2026
378.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1519
24.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2354
38.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
3030
49.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
8057
9.40 IPS |
|
|
Pose Estimation (HP)
|
100% |
17501
20.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
14942
17.5 IPS |
|
|
Object Detection (SP)
|
100% |
1680
133.3 IPS |
|
|
Object Detection (HP)
|
97% |
3261
259.6 IPS |
|
|
Object Detection (Q)
|
94% |
2353
187.6 IPS |
|
|
Face Detection (SP)
|
100% |
3050
36.2 IPS |
|
|
Face Detection (HP)
|
100% |
6732
80.0 IPS |
|
|
Face Detection (Q)
|
100% |
3845
45.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
6729
51.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
12618
97.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
8952
70.0 IPS |
|
|
Style Transfer (SP)
|
100% |
21833
28.1 IPS |
|
|
Style Transfer (HP)
|
100% |
34260
44.0 IPS |
|
|
Style Transfer (Q)
|
96% |
28249
36.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4824
178.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5684
209.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4380
161.7 IPS |
|
|
Text Classification (SP)
|
100% |
3184
4.25 KIPS |
|
|
Text Classification (HP)
|
99% |
5511
7.36 KIPS |
|
|
Text Classification (Q)
|
93% |
5651
7.58 KIPS |
|
|
Machine Translation (SP)
|
100% |
3062
52.7 IPS |
|
|
Machine Translation (HP)
|
98% |
7049
121.8 IPS |
|
|
Machine Translation (Q)
|
98% |
7046
121.8 IPS |