User | wangxin |
Upload Date | December 05 2024 02:25 PM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5089c) |
Model | Mac mini (2024) |
Model ID | Mac16,10 |
Motherboard | Mac16,10 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2006
373.1 IPS |
|
Image Classification (HP)
|
100% |
18386
3.42 KIPS |
|
Image Classification (Q)
|
97% |
27071
5.05 KIPS |
|
Image Segmentation (SP)
|
100% |
2070
33.6 IPS |
|
Image Segmentation (HP)
|
100% |
21375
346.5 IPS |
|
Image Segmentation (Q)
|
99% |
30346
491.9 IPS |
|
Pose Estimation (SP)
|
100% |
9920
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
123791
144.4 IPS |
|
Pose Estimation (Q)
|
95% |
233003
273.1 IPS |
|
Object Detection (SP)
|
100% |
2281
181.0 IPS |
|
Object Detection (HP)
|
100% |
18280
1.45 KIPS |
|
Object Detection (Q)
|
91% |
25599
2.05 KIPS |
|
Face Detection (SP)
|
100% |
3977
47.3 IPS |
|
Face Detection (HP)
|
100% |
43204
513.4 IPS |
|
Face Detection (Q)
|
100% |
61095
725.9 IPS |
|
Depth Estimation (SP)
|
100% |
8327
64.2 IPS |
|
Depth Estimation (HP)
|
99% |
99099
763.5 IPS |
|
Depth Estimation (Q)
|
85% |
169133
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
25123
32.3 IPS |
|
Style Transfer (HP)
|
100% |
235055
302.2 IPS |
|
Style Transfer (Q)
|
96% |
300511
387.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5728
211.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
49361
1.82 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83845
3.10 KIPS |
|
Text Classification (SP)
|
100% |
2937
3.92 KIPS |
|
Text Classification (HP)
|
100% |
6255
8.35 KIPS |
|
Text Classification (Q)
|
93% |
5711
7.66 KIPS |
|
Machine Translation (SP)
|
100% |
3899
67.2 IPS |
|
Machine Translation (HP)
|
100% |
16331
281.3 IPS |
|
Machine Translation (Q)
|
98% |
17835
308.2 IPS |