User | wewe |
Upload Date | February 12 2025 10:35 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 2.61 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1462
271.9 IPS |
|
Image Classification (HP)
|
100% |
13436
2.50 KIPS |
|
Image Classification (Q)
|
97% |
16437
3.07 KIPS |
|
Image Segmentation (SP)
|
100% |
1748
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
17030
276.1 IPS |
|
Image Segmentation (Q)
|
99% |
22664
367.4 IPS |
|
Pose Estimation (SP)
|
100% |
12972
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
91049
106.2 IPS |
|
Pose Estimation (Q)
|
95% |
174121
204.1 IPS |
|
Object Detection (SP)
|
100% |
1750
138.8 IPS |
|
Object Detection (HP)
|
100% |
13244
1.05 KIPS |
|
Object Detection (Q)
|
91% |
16946
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3234
38.4 IPS |
|
Face Detection (HP)
|
100% |
30102
357.7 IPS |
|
Face Detection (Q)
|
100% |
41247
490.1 IPS |
|
Depth Estimation (SP)
|
100% |
6162
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
74660
575.2 IPS |
|
Depth Estimation (Q)
|
85% |
136512
1.07 KIPS |
|
Style Transfer (SP)
|
100% |
25281
32.5 IPS |
|
Style Transfer (HP)
|
100% |
179951
231.3 IPS |
|
Style Transfer (Q)
|
96% |
216802
279.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4992
184.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
31714
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
62836
2.32 KIPS |
|
Text Classification (SP)
|
100% |
2068
2.76 KIPS |
|
Text Classification (HP)
|
100% |
3530
4.71 KIPS |
|
Text Classification (Q)
|
93% |
4110
5.52 KIPS |
|
Machine Translation (SP)
|
100% |
4130
71.1 IPS |
|
Machine Translation (HP)
|
100% |
9985
172.0 IPS |
|
Machine Translation (Q)
|
98% |
10107
174.7 IPS |