Upload Date | September 17 2024 12:55 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
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 | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1564
290.9 IPS |
|
Image Classification (HP)
|
100% |
2797
520.2 IPS |
|
Image Classification (Q)
|
99% |
2800
522.3 IPS |
|
Image Segmentation (SP)
|
100% |
1976
32.0 IPS |
|
Image Segmentation (HP)
|
100% |
2984
48.4 IPS |
|
Image Segmentation (Q)
|
100% |
3030
49.1 IPS |
|
Pose Estimation (SP)
|
100% |
8860
10.3 IPS |
|
Pose Estimation (HP)
|
100% |
17201
20.1 IPS |
|
Pose Estimation (Q)
|
96% |
14654
17.2 IPS |
|
Object Detection (SP)
|
100% |
1828
145.0 IPS |
|
Object Detection (HP)
|
97% |
3183
253.4 IPS |
|
Object Detection (Q)
|
94% |
2279
181.6 IPS |
|
Face Detection (SP)
|
100% |
3685
43.8 IPS |
|
Face Detection (HP)
|
100% |
6660
79.1 IPS |
|
Face Detection (Q)
|
100% |
3955
47.0 IPS |
|
Depth Estimation (SP)
|
100% |
7193
55.4 IPS |
|
Depth Estimation (HP)
|
98% |
13368
103.3 IPS |
|
Depth Estimation (Q)
|
97% |
13341
103.2 IPS |
|
Style Transfer (SP)
|
100% |
22378
28.8 IPS |
|
Style Transfer (HP)
|
100% |
33362
42.9 IPS |
|
Style Transfer (Q)
|
100% |
33434
43.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5245
193.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
5885
217.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
4214
156.1 IPS |
|
Text Classification (SP)
|
100% |
2815
3.76 KIPS |
|
Text Classification (HP)
|
100% |
4900
6.54 KIPS |
|
Text Classification (Q)
|
93% |
4856
6.52 KIPS |
|
Machine Translation (SP)
|
100% |
3594
61.9 IPS |
|
Machine Translation (HP)
|
98% |
6398
110.5 IPS |
|
Machine Translation (Q)
|
98% |
6400
110.6 IPS |