User | mkennedy |
Upload Date | February 21 2025 05:30 PM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 3.47 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1395
259.5 IPS |
|
Image Classification (HP)
|
100% |
14363
2.67 KIPS |
|
Image Classification (Q)
|
96% |
17150
3.20 KIPS |
|
Image Segmentation (SP)
|
100% |
1704
27.6 IPS |
|
Image Segmentation (HP)
|
100% |
19686
319.1 IPS |
|
Image Segmentation (Q)
|
99% |
24679
400.1 IPS |
|
Pose Estimation (SP)
|
100% |
12818
15.0 IPS |
|
Pose Estimation (HP)
|
100% |
106336
124.1 IPS |
|
Pose Estimation (Q)
|
95% |
104697
122.7 IPS |
|
Object Detection (SP)
|
100% |
1663
131.9 IPS |
|
Object Detection (HP)
|
99% |
15733
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17079
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3543
42.1 IPS |
|
Face Detection (HP)
|
100% |
35451
421.2 IPS |
|
Face Detection (Q)
|
100% |
45752
543.6 IPS |
|
Depth Estimation (SP)
|
100% |
6412
49.4 IPS |
|
Depth Estimation (HP)
|
99% |
87686
675.6 IPS |
|
Depth Estimation (Q)
|
85% |
109149
853.0 IPS |
|
Style Transfer (SP)
|
100% |
24576
31.6 IPS |
|
Style Transfer (HP)
|
100% |
203026
261.0 IPS |
|
Style Transfer (Q)
|
96% |
194836
251.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5103
188.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
41684
1.54 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50372
1.86 KIPS |
|
Text Classification (SP)
|
100% |
2279
3.04 KIPS |
|
Text Classification (HP)
|
100% |
4037
5.39 KIPS |
|
Text Classification (Q)
|
93% |
4016
5.39 KIPS |
|
Machine Translation (SP)
|
100% |
4400
75.8 IPS |
|
Machine Translation (HP)
|
100% |
4213
72.6 IPS |
|
Machine Translation (Q)
|
98% |
4419
76.4 IPS |