Upload Date | August 24 2025 10:20 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.6 |
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% |
1368
254.4 IPS |
|
Image Classification (HP)
|
100% |
10438
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12197
2.28 KIPS |
|
Image Segmentation (SP)
|
100% |
1414
22.9 IPS |
|
Image Segmentation (HP)
|
100% |
13435
217.8 IPS |
|
Image Segmentation (Q)
|
99% |
19284
312.6 IPS |
|
Pose Estimation (SP)
|
100% |
6583
7.68 IPS |
|
Pose Estimation (HP)
|
100% |
104121
121.5 IPS |
|
Pose Estimation (Q)
|
95% |
103705
121.5 IPS |
|
Object Detection (SP)
|
100% |
1571
124.6 IPS |
|
Object Detection (HP)
|
100% |
13364
1.06 KIPS |
|
Object Detection (Q)
|
91% |
16088
1.29 KIPS |
|
Face Detection (SP)
|
100% |
3000
35.6 IPS |
|
Face Detection (HP)
|
100% |
31397
373.1 IPS |
|
Face Detection (Q)
|
100% |
40381
479.8 IPS |
|
Depth Estimation (SP)
|
100% |
6130
47.2 IPS |
|
Depth Estimation (HP)
|
99% |
75880
584.6 IPS |
|
Depth Estimation (Q)
|
85% |
97433
761.8 IPS |
|
Style Transfer (SP)
|
100% |
18240
23.4 IPS |
|
Style Transfer (HP)
|
100% |
177438
228.1 IPS |
|
Style Transfer (Q)
|
96% |
183113
236.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4188
154.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
32261
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38024
1.40 KIPS |
|
Text Classification (SP)
|
100% |
2730
3.64 KIPS |
|
Text Classification (HP)
|
100% |
2510
3.35 KIPS |
|
Text Classification (Q)
|
93% |
2850
3.82 KIPS |
|
Machine Translation (SP)
|
100% |
3523
60.7 IPS |
|
Machine Translation (HP)
|
100% |
7468
128.6 IPS |
|
Machine Translation (Q)
|
98% |
8649
149.5 IPS |