User | lechnowak |
Upload Date | November 20 2024 06:53 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,6 |
Motherboard | Mac15,6 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 11 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 5 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1588
295.3 IPS |
|
Image Classification (HP)
|
100% |
15805
2.94 KIPS |
|
Image Classification (Q)
|
97% |
19173
3.58 KIPS |
|
Image Segmentation (SP)
|
100% |
1895
30.7 IPS |
|
Image Segmentation (HP)
|
100% |
21668
351.2 IPS |
|
Image Segmentation (Q)
|
99% |
27567
446.9 IPS |
|
Pose Estimation (SP)
|
100% |
8949
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
121383
141.6 IPS |
|
Pose Estimation (Q)
|
95% |
119995
140.6 IPS |
|
Object Detection (SP)
|
100% |
1844
146.3 IPS |
|
Object Detection (HP)
|
100% |
17302
1.37 KIPS |
|
Object Detection (Q)
|
91% |
20593
1.65 KIPS |
|
Face Detection (SP)
|
100% |
3742
44.5 IPS |
|
Face Detection (HP)
|
100% |
38065
452.3 IPS |
|
Face Detection (Q)
|
100% |
50530
600.4 IPS |
|
Depth Estimation (SP)
|
100% |
7253
55.9 IPS |
|
Depth Estimation (HP)
|
99% |
97023
747.5 IPS |
|
Depth Estimation (Q)
|
85% |
121207
947.6 IPS |
|
Style Transfer (SP)
|
100% |
22376
28.8 IPS |
|
Style Transfer (HP)
|
100% |
225220
289.5 IPS |
|
Style Transfer (Q)
|
96% |
218679
282.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5236
193.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
45780
1.69 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56484
2.09 KIPS |
|
Text Classification (SP)
|
100% |
2802
3.74 KIPS |
|
Text Classification (HP)
|
100% |
4874
6.51 KIPS |
|
Text Classification (Q)
|
93% |
4926
6.61 KIPS |
|
Machine Translation (SP)
|
100% |
3543
61.0 IPS |
|
Machine Translation (HP)
|
100% |
8486
146.2 IPS |
|
Machine Translation (Q)
|
98% |
9389
162.3 IPS |