User | geekbenchmonk |
Upload Date | March 28 2025 03:19 PM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
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% |
1943
361.4 IPS |
|
Image Classification (HP)
|
100% |
18824
3.50 KIPS |
|
Image Classification (Q)
|
97% |
26242
4.90 KIPS |
|
Image Segmentation (SP)
|
100% |
2057
33.3 IPS |
|
Image Segmentation (HP)
|
100% |
21636
350.7 IPS |
|
Image Segmentation (Q)
|
99% |
30199
489.6 IPS |
|
Pose Estimation (SP)
|
100% |
9712
11.3 IPS |
|
Pose Estimation (HP)
|
100% |
122728
143.2 IPS |
|
Pose Estimation (Q)
|
95% |
231844
271.7 IPS |
|
Object Detection (SP)
|
100% |
2148
170.4 IPS |
|
Object Detection (HP)
|
100% |
19014
1.51 KIPS |
|
Object Detection (Q)
|
91% |
27676
2.21 KIPS |
|
Face Detection (SP)
|
100% |
3697
43.9 IPS |
|
Face Detection (HP)
|
100% |
44379
527.3 IPS |
|
Face Detection (Q)
|
100% |
61431
729.9 IPS |
|
Depth Estimation (SP)
|
100% |
8224
63.4 IPS |
|
Depth Estimation (HP)
|
99% |
99384
765.7 IPS |
|
Depth Estimation (Q)
|
85% |
171367
1.34 KIPS |
|
Style Transfer (SP)
|
100% |
24943
32.1 IPS |
|
Style Transfer (HP)
|
100% |
233835
300.6 IPS |
|
Style Transfer (Q)
|
96% |
300781
388.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5769
213.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
50765
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
89689
3.31 KIPS |
|
Text Classification (SP)
|
100% |
3036
4.05 KIPS |
|
Text Classification (HP)
|
100% |
7311
9.76 KIPS |
|
Text Classification (Q)
|
93% |
6873
9.22 KIPS |
|
Machine Translation (SP)
|
100% |
3804
65.5 IPS |
|
Machine Translation (HP)
|
100% |
16324
281.2 IPS |
|
Machine Translation (Q)
|
98% |
17927
309.8 IPS |