Upload Date | July 11 2025 08:33 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2065
384.1 IPS |
|
Image Classification (HP)
|
100% |
17595
3.27 KIPS |
|
Image Classification (Q)
|
97% |
24224
4.52 KIPS |
|
Image Segmentation (SP)
|
100% |
2260
36.6 IPS |
|
Image Segmentation (HP)
|
100% |
23256
377.0 IPS |
|
Image Segmentation (Q)
|
99% |
32211
522.2 IPS |
|
Pose Estimation (SP)
|
100% |
17192
20.1 IPS |
|
Pose Estimation (HP)
|
100% |
122676
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
229891
269.4 IPS |
|
Object Detection (SP)
|
100% |
2485
197.1 IPS |
|
Object Detection (HP)
|
100% |
19920
1.58 KIPS |
|
Object Detection (Q)
|
91% |
24285
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4609
54.8 IPS |
|
Face Detection (HP)
|
100% |
45778
543.9 IPS |
|
Face Detection (Q)
|
100% |
64575
767.3 IPS |
|
Depth Estimation (SP)
|
100% |
8632
66.5 IPS |
|
Depth Estimation (HP)
|
99% |
113747
876.3 IPS |
|
Depth Estimation (Q)
|
85% |
181572
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
25891
33.3 IPS |
|
Style Transfer (HP)
|
100% |
236811
304.4 IPS |
|
Style Transfer (Q)
|
96% |
303691
391.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5986
221.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
47876
1.77 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79414
2.93 KIPS |
|
Text Classification (SP)
|
100% |
2900
3.87 KIPS |
|
Text Classification (HP)
|
100% |
5316
7.10 KIPS |
|
Text Classification (Q)
|
93% |
6723
9.02 KIPS |
|
Machine Translation (SP)
|
100% |
5587
96.2 IPS |
|
Machine Translation (HP)
|
100% |
17204
296.3 IPS |
|
Machine Translation (Q)
|
98% |
17152
296.4 IPS |