User | Chineezze |
Upload Date | March 19 2025 10:58 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1589
295.5 IPS |
|
Image Classification (HP)
|
100% |
16070
2.99 KIPS |
|
Image Classification (Q)
|
97% |
19124
3.57 KIPS |
|
Image Segmentation (SP)
|
100% |
1898
30.8 IPS |
|
Image Segmentation (HP)
|
100% |
21756
352.7 IPS |
|
Image Segmentation (Q)
|
99% |
27422
444.5 IPS |
|
Pose Estimation (SP)
|
100% |
8955
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
120949
141.1 IPS |
|
Pose Estimation (Q)
|
95% |
119842
140.5 IPS |
|
Object Detection (SP)
|
100% |
1842
146.1 IPS |
|
Object Detection (HP)
|
100% |
17131
1.36 KIPS |
|
Object Detection (Q)
|
91% |
19917
1.59 KIPS |
|
Face Detection (SP)
|
100% |
3724
44.2 IPS |
|
Face Detection (HP)
|
100% |
38758
460.5 IPS |
|
Face Detection (Q)
|
100% |
49931
593.3 IPS |
|
Depth Estimation (SP)
|
100% |
7251
55.9 IPS |
|
Depth Estimation (HP)
|
99% |
96891
746.5 IPS |
|
Depth Estimation (Q)
|
85% |
120963
945.7 IPS |
|
Style Transfer (SP)
|
100% |
22427
28.8 IPS |
|
Style Transfer (HP)
|
100% |
227043
291.9 IPS |
|
Style Transfer (Q)
|
96% |
219840
283.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5300
195.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
44698
1.65 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54486
2.01 KIPS |
|
Text Classification (SP)
|
100% |
2845
3.80 KIPS |
|
Text Classification (HP)
|
100% |
4990
6.66 KIPS |
|
Text Classification (Q)
|
93% |
4991
6.70 KIPS |
|
Machine Translation (SP)
|
100% |
3711
63.9 IPS |
|
Machine Translation (HP)
|
100% |
4659
80.2 IPS |
|
Machine Translation (Q)
|
98% |
4796
82.9 IPS |