Upload Date | June 14 2025 12:47 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 16.0 (Build 25A5279m) |
Model | Mac mini (2023) |
Model ID | Mac14,12 |
Motherboard | Mac14,12 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.48 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4918
914.6 IPS |
|
Image Classification (HP)
|
100% |
5096
947.8 IPS |
|
Image Classification (Q)
|
96% |
4768
890.3 IPS |
|
Image Segmentation (SP)
|
100% |
8290
134.4 IPS |
|
Image Segmentation (HP)
|
100% |
8234
133.5 IPS |
|
Image Segmentation (Q)
|
99% |
7948
128.8 IPS |
|
Pose Estimation (SP)
|
100% |
36943
43.1 IPS |
|
Pose Estimation (HP)
|
100% |
40702
47.5 IPS |
|
Pose Estimation (Q)
|
96% |
39407
46.2 IPS |
|
Object Detection (SP)
|
100% |
4764
377.9 IPS |
|
Object Detection (HP)
|
100% |
4992
395.9 IPS |
|
Object Detection (Q)
|
92% |
4466
356.5 IPS |
|
Face Detection (SP)
|
100% |
16989
201.9 IPS |
|
Face Detection (HP)
|
100% |
17530
208.3 IPS |
|
Face Detection (Q)
|
100% |
15231
181.0 IPS |
|
Depth Estimation (SP)
|
100% |
24404
188.0 IPS |
|
Depth Estimation (HP)
|
99% |
25691
197.9 IPS |
|
Depth Estimation (Q)
|
86% |
23546
183.9 IPS |
|
Style Transfer (SP)
|
100% |
68156
87.6 IPS |
|
Style Transfer (HP)
|
100% |
75583
97.2 IPS |
|
Style Transfer (Q)
|
96% |
73975
95.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
13252
489.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
14301
528.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
12498
461.5 IPS |
|
Text Classification (SP)
|
100% |
2322
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3927
5.24 KIPS |
|
Text Classification (Q)
|
93% |
3875
5.20 KIPS |
|
Machine Translation (SP)
|
100% |
3401
58.6 IPS |
|
Machine Translation (HP)
|
100% |
3502
60.3 IPS |
|
Machine Translation (Q)
|
98% |
3468
59.9 IPS |