User | andrijan |
Upload Date | April 17 2025 01:37 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
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 | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2052
381.5 IPS |
|
Image Classification (HP)
|
100% |
18802
3.50 KIPS |
|
Image Classification (Q)
|
97% |
28211
5.26 KIPS |
|
Image Segmentation (SP)
|
100% |
2166
35.1 IPS |
|
Image Segmentation (HP)
|
100% |
22401
363.1 IPS |
|
Image Segmentation (Q)
|
99% |
30785
499.0 IPS |
|
Pose Estimation (SP)
|
100% |
9725
11.3 IPS |
|
Pose Estimation (HP)
|
100% |
122958
143.5 IPS |
|
Pose Estimation (Q)
|
95% |
231146
270.9 IPS |
|
Object Detection (SP)
|
100% |
2439
193.4 IPS |
|
Object Detection (HP)
|
100% |
19570
1.55 KIPS |
|
Object Detection (Q)
|
91% |
27249
2.18 KIPS |
|
Face Detection (SP)
|
100% |
4302
51.1 IPS |
|
Face Detection (HP)
|
100% |
45533
541.0 IPS |
|
Face Detection (Q)
|
100% |
66721
792.8 IPS |
|
Depth Estimation (SP)
|
100% |
8720
67.2 IPS |
|
Depth Estimation (HP)
|
99% |
100152
771.6 IPS |
|
Depth Estimation (Q)
|
85% |
172354
1.35 KIPS |
|
Style Transfer (SP)
|
100% |
20852
26.8 IPS |
|
Style Transfer (HP)
|
100% |
237405
305.2 IPS |
|
Style Transfer (Q)
|
96% |
299865
387.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5907
218.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
50867
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
88268
3.26 KIPS |
|
Text Classification (SP)
|
100% |
2946
3.93 KIPS |
|
Text Classification (HP)
|
100% |
6855
9.15 KIPS |
|
Text Classification (Q)
|
93% |
7104
9.53 KIPS |
|
Machine Translation (SP)
|
100% |
4380
75.4 IPS |
|
Machine Translation (HP)
|
100% |
16868
290.6 IPS |
|
Machine Translation (Q)
|
98% |
19050
329.2 IPS |