Upload Date | September 01 2025 05:09 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | Mac15,12 |
Model ID | Mac15,12 |
Motherboard | Mac15,12 |
CPU Information | |
---|---|
Name | Apple M3 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M3 |
Base Frequency | 4.05 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1595
296.6 IPS |
|
Image Classification (HP)
|
100% |
17845
3.32 KIPS |
|
Image Classification (Q)
|
97% |
20706
3.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1890
30.6 IPS |
|
Image Segmentation (HP)
|
100% |
22008
356.8 IPS |
|
Image Segmentation (Q)
|
99% |
27168
440.4 IPS |
|
Pose Estimation (SP)
|
100% |
8895
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
121903
142.2 IPS |
|
Pose Estimation (Q)
|
95% |
121003
141.8 IPS |
|
Object Detection (SP)
|
100% |
1831
145.2 IPS |
|
Object Detection (HP)
|
100% |
18555
1.47 KIPS |
|
Object Detection (Q)
|
91% |
20924
1.67 KIPS |
|
Face Detection (SP)
|
100% |
3509
41.7 IPS |
|
Face Detection (HP)
|
100% |
38119
452.9 IPS |
|
Face Detection (Q)
|
100% |
52064
618.6 IPS |
|
Depth Estimation (SP)
|
100% |
7083
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
98815
761.3 IPS |
|
Depth Estimation (Q)
|
85% |
126418
988.4 IPS |
|
Style Transfer (SP)
|
100% |
22417
28.8 IPS |
|
Style Transfer (HP)
|
100% |
228244
293.4 IPS |
|
Style Transfer (Q)
|
96% |
220194
284.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5286
195.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
48271
1.78 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57820
2.14 KIPS |
|
Text Classification (SP)
|
100% |
2995
4.00 KIPS |
|
Text Classification (HP)
|
100% |
5448
7.27 KIPS |
|
Text Classification (Q)
|
93% |
5427
7.28 KIPS |
|
Machine Translation (SP)
|
100% |
3260
56.2 IPS |
|
Machine Translation (HP)
|
100% |
4596
79.2 IPS |
|
Machine Translation (Q)
|
98% |
4794
82.9 IPS |