| User | M91 |
| Upload Date | November 09 2024 08:36 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.51 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1643
305.5 IPS |
|
|
Image Classification (HP)
|
100% |
1492
277.5 IPS |
|
|
Image Classification (Q)
|
97% |
1468
273.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
2225
36.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2514
40.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
2465
40.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
11701
13.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
12345
14.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
11370
13.3 IPS |
|
|
Object Detection (SP)
|
100% |
1940
153.9 IPS |
|
|
Object Detection (HP)
|
100% |
1923
152.5 IPS |
|
|
Object Detection (Q)
|
91% |
1547
123.6 IPS |
|
|
Face Detection (SP)
|
100% |
5179
61.5 IPS |
|
|
Face Detection (HP)
|
100% |
5956
70.8 IPS |
|
|
Face Detection (Q)
|
100% |
4091
48.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
8427
64.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
8863
68.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
7180
56.1 IPS |
|
|
Style Transfer (SP)
|
100% |
21199
27.3 IPS |
|
|
Style Transfer (HP)
|
100% |
23803
30.6 IPS |
|
|
Style Transfer (Q)
|
96% |
22013
28.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4863
179.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4790
176.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3763
138.9 IPS |
|
|
Text Classification (SP)
|
100% |
2644
3.53 KIPS |
|
|
Text Classification (HP)
|
100% |
4681
6.25 KIPS |
|
|
Text Classification (Q)
|
93% |
4639
6.23 KIPS |
|
|
Machine Translation (SP)
|
100% |
792
13.6 IPS |
|
|
Machine Translation (HP)
|
100% |
798
13.7 IPS |
|
|
Machine Translation (Q)
|
98% |
738
12.8 IPS |