User | AlexeySukhanov |
Upload Date | June 10 2025 03:11 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
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 | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2090
388.7 IPS |
|
Image Classification (HP)
|
100% |
18048
3.36 KIPS |
|
Image Classification (Q)
|
97% |
22453
4.19 KIPS |
|
Image Segmentation (SP)
|
100% |
2355
38.2 IPS |
|
Image Segmentation (HP)
|
100% |
23309
377.9 IPS |
|
Image Segmentation (Q)
|
99% |
32369
524.7 IPS |
|
Pose Estimation (SP)
|
100% |
17197
20.1 IPS |
|
Pose Estimation (HP)
|
100% |
122798
143.3 IPS |
|
Pose Estimation (Q)
|
95% |
230134
269.7 IPS |
|
Object Detection (SP)
|
100% |
2481
196.8 IPS |
|
Object Detection (HP)
|
100% |
20420
1.62 KIPS |
|
Object Detection (Q)
|
91% |
23845
1.91 KIPS |
|
Face Detection (SP)
|
100% |
4620
54.9 IPS |
|
Face Detection (HP)
|
100% |
45960
546.1 IPS |
|
Face Detection (Q)
|
100% |
64123
761.9 IPS |
|
Depth Estimation (SP)
|
100% |
8667
66.8 IPS |
|
Depth Estimation (HP)
|
99% |
111659
860.3 IPS |
|
Depth Estimation (Q)
|
85% |
178774
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
25280
32.5 IPS |
|
Style Transfer (HP)
|
100% |
239014
307.3 IPS |
|
Style Transfer (Q)
|
96% |
304103
392.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
6014
222.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
46871
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82190
3.03 KIPS |
|
Text Classification (SP)
|
100% |
2879
3.84 KIPS |
|
Text Classification (HP)
|
100% |
5301
7.08 KIPS |
|
Text Classification (Q)
|
93% |
5724
7.68 KIPS |
|
Machine Translation (SP)
|
100% |
5696
98.1 IPS |
|
Machine Translation (HP)
|
100% |
16766
288.8 IPS |
|
Machine Translation (Q)
|
98% |
17173
296.8 IPS |