User | fmejia01 |
Upload Date | July 28 2025 06:48 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1611
299.5 IPS |
|
Image Classification (HP)
|
100% |
16654
3.10 KIPS |
|
Image Classification (Q)
|
97% |
20682
3.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1862
30.2 IPS |
|
Image Segmentation (HP)
|
100% |
22471
364.3 IPS |
|
Image Segmentation (Q)
|
99% |
27935
452.9 IPS |
|
Pose Estimation (SP)
|
100% |
8988
10.5 IPS |
|
Pose Estimation (HP)
|
100% |
120525
140.6 IPS |
|
Pose Estimation (Q)
|
95% |
120498
141.2 IPS |
|
Object Detection (SP)
|
100% |
1815
143.9 IPS |
|
Object Detection (HP)
|
100% |
17806
1.41 KIPS |
|
Object Detection (Q)
|
91% |
20640
1.65 KIPS |
|
Face Detection (SP)
|
100% |
3758
44.7 IPS |
|
Face Detection (HP)
|
100% |
37932
450.7 IPS |
|
Face Detection (Q)
|
100% |
49857
592.4 IPS |
|
Depth Estimation (SP)
|
100% |
7141
55.0 IPS |
|
Depth Estimation (HP)
|
99% |
97305
749.7 IPS |
|
Depth Estimation (Q)
|
85% |
122791
960.0 IPS |
|
Style Transfer (SP)
|
100% |
22282
28.6 IPS |
|
Style Transfer (HP)
|
100% |
227778
292.8 IPS |
|
Style Transfer (Q)
|
96% |
220325
284.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5278
194.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46109
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59149
2.18 KIPS |
|
Text Classification (SP)
|
100% |
2908
3.88 KIPS |
|
Text Classification (HP)
|
100% |
5301
7.08 KIPS |
|
Text Classification (Q)
|
93% |
5177
6.95 KIPS |
|
Machine Translation (SP)
|
100% |
3428
59.1 IPS |
|
Machine Translation (HP)
|
100% |
4899
84.4 IPS |
|
Machine Translation (Q)
|
98% |
5103
88.2 IPS |