User | ___ |
Upload Date | June 10 2025 09:52 AM |
Views | 6 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD RYZEN AI MAX+ 395 w/ Radeon 8060S |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | GMKtec NucBox_EVO-X2 |
Motherboard | GMKtec GMKtec |
CPU Information | |
---|---|
Name | AMD Ryzen AI Max+ 395 |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | AuthenticAMD Family 26 Model 112 Stepping 0 |
Base Frequency | 3.00 GHz |
Cluster 1 | 16 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4813
895.1 IPS |
|
Image Classification (HP)
|
100% |
615
114.3 IPS |
|
Image Classification (Q)
|
99% |
11393
2.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1035
16.8 IPS |
|
Image Segmentation (HP)
|
100% |
967
15.7 IPS |
|
Image Segmentation (Q)
|
98% |
3221
52.4 IPS |
|
Pose Estimation (SP)
|
100% |
13766
16.1 IPS |
|
Pose Estimation (HP)
|
100% |
9969
11.6 IPS |
|
Pose Estimation (Q)
|
94% |
45111
52.9 IPS |
|
Object Detection (SP)
|
100% |
4413
350.0 IPS |
|
Object Detection (HP)
|
100% |
809
64.1 IPS |
|
Object Detection (Q)
|
86% |
12169
978.0 IPS |
|
Face Detection (SP)
|
100% |
10327
122.7 IPS |
|
Face Detection (HP)
|
100% |
1794
21.3 IPS |
|
Face Detection (Q)
|
97% |
12748
152.0 IPS |
|
Depth Estimation (SP)
|
100% |
14683
113.1 IPS |
|
Depth Estimation (HP)
|
99% |
2751
21.2 IPS |
|
Depth Estimation (Q)
|
78% |
10304
82.2 IPS |
|
Style Transfer (SP)
|
100% |
27967
36.0 IPS |
|
Style Transfer (HP)
|
100% |
24010
30.9 IPS |
|
Style Transfer (Q)
|
98% |
47383
61.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3960
146.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
3077
113.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
4231
156.7 IPS |
|
Text Classification (SP)
|
100% |
1894
2.53 KIPS |
|
Text Classification (HP)
|
100% |
907
1.21 KIPS |
|
Text Classification (Q)
|
97% |
1784
2.39 KIPS |
|
Machine Translation (SP)
|
100% |
2974
51.2 IPS |
|
Machine Translation (HP)
|
100% |
797
13.7 IPS |
|
Machine Translation (Q)
|
65% |
4335
87.1 IPS |