User | macbookjoe |
Upload Date | September 15 2025 06:56 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | Mac mini (2023) |
Model ID | Mac14,3 |
Motherboard | Mac14,3 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3700
688.1 IPS |
|
Image Classification (HP)
|
100% |
3710
690.0 IPS |
|
Image Classification (Q)
|
96% |
3470
648.0 IPS |
|
Image Segmentation (SP)
|
100% |
5719
92.7 IPS |
|
Image Segmentation (HP)
|
100% |
5888
95.4 IPS |
|
Image Segmentation (Q)
|
99% |
5611
91.0 IPS |
|
Pose Estimation (SP)
|
100% |
24648
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26759
31.2 IPS |
|
Pose Estimation (Q)
|
96% |
26003
30.5 IPS |
|
Object Detection (SP)
|
100% |
3639
288.7 IPS |
|
Object Detection (HP)
|
100% |
3761
298.3 IPS |
|
Object Detection (Q)
|
92% |
3394
270.9 IPS |
|
Face Detection (SP)
|
100% |
10423
123.8 IPS |
|
Face Detection (HP)
|
100% |
12409
147.4 IPS |
|
Face Detection (Q)
|
100% |
10046
119.4 IPS |
|
Depth Estimation (SP)
|
100% |
16790
129.4 IPS |
|
Depth Estimation (HP)
|
99% |
18182
140.1 IPS |
|
Depth Estimation (Q)
|
86% |
16680
130.3 IPS |
|
Style Transfer (SP)
|
100% |
42072
54.1 IPS |
|
Style Transfer (HP)
|
100% |
49326
63.4 IPS |
|
Style Transfer (Q)
|
96% |
47827
61.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
9842
363.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
10281
379.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
9140
337.5 IPS |
|
Text Classification (SP)
|
100% |
2364
3.16 KIPS |
|
Text Classification (HP)
|
100% |
3858
5.15 KIPS |
|
Text Classification (Q)
|
93% |
3936
5.28 KIPS |
|
Machine Translation (SP)
|
100% |
2056
35.4 IPS |
|
Machine Translation (HP)
|
100% |
2171
37.4 IPS |
|
Machine Translation (Q)
|
98% |
2163
37.4 IPS |