Upload Date | December 21 2024 02:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D5034f) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,3 |
Motherboard | Mac15,3 |
CPU Information | |
---|---|
Name | Apple M3 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M3 |
Base Frequency | 4.03 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4091
760.7 IPS |
|
Image Classification (HP)
|
100% |
4455
828.5 IPS |
|
Image Classification (Q)
|
97% |
3863
721.0 IPS |
|
Image Segmentation (SP)
|
100% |
3972
64.4 IPS |
|
Image Segmentation (HP)
|
100% |
5719
92.7 IPS |
|
Image Segmentation (Q)
|
99% |
6210
100.7 IPS |
|
Pose Estimation (SP)
|
100% |
24020
28.0 IPS |
|
Pose Estimation (HP)
|
100% |
26035
30.4 IPS |
|
Pose Estimation (Q)
|
95% |
24704
29.0 IPS |
|
Object Detection (SP)
|
100% |
4204
333.5 IPS |
|
Object Detection (HP)
|
100% |
4610
365.6 IPS |
|
Object Detection (Q)
|
91% |
3968
317.1 IPS |
|
Face Detection (SP)
|
100% |
10612
126.1 IPS |
|
Face Detection (HP)
|
100% |
14391
171.0 IPS |
|
Face Detection (Q)
|
100% |
10508
124.9 IPS |
|
Depth Estimation (SP)
|
100% |
17714
136.5 IPS |
|
Depth Estimation (HP)
|
99% |
19957
153.8 IPS |
|
Depth Estimation (Q)
|
85% |
17187
134.3 IPS |
|
Style Transfer (SP)
|
100% |
50418
64.8 IPS |
|
Style Transfer (HP)
|
100% |
58979
75.8 IPS |
|
Style Transfer (Q)
|
96% |
55068
71.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
10575
390.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
11540
426.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
9124
336.9 IPS |
|
Text Classification (SP)
|
100% |
2879
3.84 KIPS |
|
Text Classification (HP)
|
100% |
5043
6.73 KIPS |
|
Text Classification (Q)
|
93% |
4971
6.67 KIPS |
|
Machine Translation (SP)
|
100% |
1457
25.1 IPS |
|
Machine Translation (HP)
|
100% |
1529
26.3 IPS |
|
Machine Translation (Q)
|
98% |
1773
30.6 IPS |