User | saronian |
Upload Date | January 26 2025 01:33 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2087
388.1 IPS |
|
Image Classification (HP)
|
100% |
17533
3.26 KIPS |
|
Image Classification (Q)
|
97% |
21939
4.09 KIPS |
|
Image Segmentation (SP)
|
100% |
2495
40.4 IPS |
|
Image Segmentation (HP)
|
100% |
23376
378.9 IPS |
|
Image Segmentation (Q)
|
99% |
32128
520.8 IPS |
|
Pose Estimation (SP)
|
100% |
18896
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123510
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
231625
271.5 IPS |
|
Object Detection (SP)
|
100% |
2487
197.3 IPS |
|
Object Detection (HP)
|
100% |
19614
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23832
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4504
53.5 IPS |
|
Face Detection (HP)
|
100% |
44596
529.9 IPS |
|
Face Detection (Q)
|
100% |
63943
759.8 IPS |
|
Depth Estimation (SP)
|
100% |
8841
68.1 IPS |
|
Depth Estimation (HP)
|
99% |
112009
863.0 IPS |
|
Depth Estimation (Q)
|
85% |
176934
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35263
45.3 IPS |
|
Style Transfer (HP)
|
100% |
238699
306.9 IPS |
|
Style Transfer (Q)
|
96% |
303269
391.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
7039
259.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46316
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78190
2.89 KIPS |
|
Text Classification (SP)
|
100% |
2926
3.91 KIPS |
|
Text Classification (HP)
|
100% |
4649
6.21 KIPS |
|
Text Classification (Q)
|
93% |
4706
6.32 KIPS |
|
Machine Translation (SP)
|
100% |
5764
99.3 IPS |
|
Machine Translation (HP)
|
100% |
16062
276.7 IPS |
|
Machine Translation (Q)
|
98% |
16087
278.0 IPS |