User | j4lber |
Upload Date | December 30 2024 10:09 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2048
380.9 IPS |
|
Image Classification (HP)
|
100% |
2983
554.8 IPS |
|
Image Classification (Q)
|
96% |
2153
402.1 IPS |
|
Image Segmentation (SP)
|
100% |
2509
40.7 IPS |
|
Image Segmentation (HP)
|
100% |
3604
58.4 IPS |
|
Image Segmentation (Q)
|
99% |
3917
63.5 IPS |
|
Pose Estimation (SP)
|
100% |
18628
21.7 IPS |
|
Pose Estimation (HP)
|
100% |
31613
36.9 IPS |
|
Pose Estimation (Q)
|
95% |
23825
27.9 IPS |
|
Object Detection (SP)
|
100% |
2413
191.4 IPS |
|
Object Detection (HP)
|
97% |
3783
301.2 IPS |
|
Object Detection (Q)
|
94% |
2640
210.4 IPS |
|
Face Detection (SP)
|
100% |
4413
52.4 IPS |
|
Face Detection (HP)
|
100% |
7577
90.0 IPS |
|
Face Detection (Q)
|
100% |
4607
54.7 IPS |
|
Depth Estimation (SP)
|
100% |
8432
65.0 IPS |
|
Depth Estimation (HP)
|
97% |
13905
107.5 IPS |
|
Depth Estimation (Q)
|
86% |
10033
78.3 IPS |
|
Style Transfer (SP)
|
100% |
35222
45.3 IPS |
|
Style Transfer (HP)
|
100% |
50260
64.6 IPS |
|
Style Transfer (Q)
|
96% |
38531
49.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6954
256.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
9524
351.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
5779
213.4 IPS |
|
Text Classification (SP)
|
100% |
2907
3.88 KIPS |
|
Text Classification (HP)
|
100% |
5091
6.80 KIPS |
|
Text Classification (Q)
|
93% |
5081
6.82 KIPS |
|
Machine Translation (SP)
|
100% |
5548
95.6 IPS |
|
Machine Translation (HP)
|
98% |
8587
148.4 IPS |
|
Machine Translation (Q)
|
98% |
8559
147.9 IPS |