Upload Date | September 17 2024 10:54 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5046f) |
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 | 3.88 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4174
776.2 IPS |
|
Image Classification (HP)
|
100% |
4502
837.2 IPS |
|
Image Classification (Q)
|
99% |
4523
843.5 IPS |
|
Image Segmentation (SP)
|
100% |
4092
66.3 IPS |
|
Image Segmentation (HP)
|
100% |
5783
93.7 IPS |
|
Image Segmentation (Q)
|
100% |
5809
94.2 IPS |
|
Pose Estimation (SP)
|
100% |
24468
28.6 IPS |
|
Pose Estimation (HP)
|
100% |
26241
30.6 IPS |
|
Pose Estimation (Q)
|
97% |
24485
28.7 IPS |
|
Object Detection (SP)
|
100% |
4250
337.1 IPS |
|
Object Detection (HP)
|
100% |
4727
375.0 IPS |
|
Object Detection (Q)
|
91% |
4003
319.8 IPS |
|
Face Detection (SP)
|
100% |
10746
127.7 IPS |
|
Face Detection (HP)
|
100% |
13695
162.7 IPS |
|
Face Detection (Q)
|
100% |
10164
120.8 IPS |
|
Depth Estimation (SP)
|
100% |
18176
140.0 IPS |
|
Depth Estimation (HP)
|
99% |
20258
156.1 IPS |
|
Depth Estimation (Q)
|
97% |
2923
22.6 IPS |
|
Style Transfer (SP)
|
100% |
50781
65.3 IPS |
|
Style Transfer (HP)
|
100% |
59548
76.5 IPS |
|
Style Transfer (Q)
|
100% |
58907
75.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
10971
405.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
11805
435.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
9151
339.0 IPS |
|
Text Classification (SP)
|
100% |
2839
3.79 KIPS |
|
Text Classification (HP)
|
100% |
5006
6.68 KIPS |
|
Text Classification (Q)
|
93% |
4995
6.70 KIPS |
|
Machine Translation (SP)
|
100% |
1653
28.5 IPS |
|
Machine Translation (HP)
|
100% |
1788
30.8 IPS |
|
Machine Translation (Q)
|
98% |
1463
25.3 IPS |