Upload Date | February 11 2025 04:35 AM |
Views | 5 |
System Information | |
---|---|
Operating System | iOS 16.2 |
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 |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 5.49 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
381
71.3 IPS |
|
Image Classification (F16)
|
100% |
395
73.9 IPS |
|
Image Classification (I8)
|
99% |
396
74.2 IPS |
|
Image Segmentation (F32)
|
100% |
294
4.90 IPS |
|
Image Segmentation (F16)
|
100% |
254
4.25 IPS |
|
Image Segmentation (I8)
|
100% |
254
4.24 IPS |
|
Pose Estimation (F32)
|
100% |
2354
2.85 IPS |
|
Pose Estimation (F16)
|
100% |
4324
5.24 IPS |
|
Pose Estimation (I8)
|
100% |
4337
5.25 IPS |
|
Object Detection (F32)
|
100% |
439
32.8 IPS |
|
Object Detection (F16)
|
100% |
452
33.8 IPS |
|
Object Detection (I8)
|
97% |
446
33.3 IPS |
|
Face Detection (F32)
|
100% |
854
10.2 IPS |
|
Face Detection (F16)
|
100% |
735
8.74 IPS |
|
Face Detection (I8)
|
99% |
742
8.82 IPS |
|
Depth Estimation (F32)
|
100% |
1476
11.4 IPS |
|
Depth Estimation (F16)
|
99% |
1641
12.7 IPS |
|
Depth Estimation (I8)
|
99% |
1623
12.6 IPS |
|
Style Transfer (F32)
|
100% |
4435
5.83 IPS |
|
Style Transfer (F16)
|
100% |
5275
6.94 IPS |
|
Style Transfer (I8)
|
100% |
5235
6.89 IPS |
|
Image Super-Resolution (F32)
|
100% |
1032
36.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
1143
40.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
1144
40.9 IPS |
|
Text Classification (F32)
|
100% |
459
659.8 IPS |
|
Text Classification (F16)
|
100% |
225
323.0 IPS |
|
Text Classification (I8)
|
96% |
308
442.5 IPS |
|
Machine Translation (F32)
|
100% |
569
10.5 IPS |
|
Machine Translation (F16)
|
99% |
780
14.4 IPS |
|
Machine Translation (I8)
|
99% |
587
10.8 IPS |