| User | M91 |
| Upload Date | December 11 2024 11:01 AM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| 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% |
1665
309.7 IPS |
|
|
Image Classification (HP)
|
100% |
1537
285.8 IPS |
|
|
Image Classification (Q)
|
97% |
1458
272.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
2265
36.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2518
40.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
2463
39.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
11697
13.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
12333
14.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
11373
13.3 IPS |
|
|
Object Detection (SP)
|
100% |
1978
156.9 IPS |
|
|
Object Detection (HP)
|
100% |
1916
152.0 IPS |
|
|
Object Detection (Q)
|
91% |
1600
127.8 IPS |
|
|
Face Detection (SP)
|
100% |
5436
64.6 IPS |
|
|
Face Detection (HP)
|
100% |
6039
71.8 IPS |
|
|
Face Detection (Q)
|
100% |
4075
48.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
8419
64.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
8801
67.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
7285
56.9 IPS |
|
|
Style Transfer (SP)
|
100% |
21147
27.2 IPS |
|
|
Style Transfer (HP)
|
100% |
23754
30.5 IPS |
|
|
Style Transfer (Q)
|
96% |
22158
28.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4724
174.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4842
178.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3736
138.0 IPS |
|
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
|
Text Classification (HP)
|
100% |
4636
6.19 KIPS |
|
|
Text Classification (Q)
|
93% |
4658
6.25 KIPS |
|
|
Machine Translation (SP)
|
100% |
788
13.6 IPS |
|
|
Machine Translation (HP)
|
100% |
799
13.8 IPS |
|
|
Machine Translation (Q)
|
98% |
793
13.7 IPS |