Geekbench ML Score

9638
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 07:11 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 (64-bit)
Model LENOVO 21KUZBUJCN
Motherboard LENOVO 21KUZBUJCN
CPU Information
Name Intel Core Ultra 9 185H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.30 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 11
L1 Data Cache48.0 KB x 11
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4050 Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4881
913.4 IPS
 
Image Classification (F16)
100% 4772
892.9 IPS
 
Image Classification (I8)
100% 4361
816.1 IPS
 
Image Segmentation (F32)
100% 6927
115.7 IPS
 
Image Segmentation (F16)
100% 5470
91.4 IPS
 
Image Segmentation (I8)
98% 4998
83.5 IPS
 
Pose Estimation (F32)
100% 44830
54.3 IPS
 
Pose Estimation (F16)
100% 57795
70.0 IPS
 
Pose Estimation (I8)
100% 53261
64.5 IPS
 
Object Detection (F32)
100% 4643
346.6 IPS
 
Object Detection (F16)
100% 3790
283.0 IPS
 
Object Detection (I8)
61% 3834
286.2 IPS
 
Face Detection (F32)
100% 13438
159.8 IPS
 
Face Detection (F16)
100% 13439
159.8 IPS
 
Face Detection (I8)
89% 11132
132.4 IPS
 
Depth Estimation (F32)
100% 25914
201.0 IPS
 
Depth Estimation (F16)
100% 26040
201.9 IPS
 
Depth Estimation (I8)
95% 16624
128.9 IPS
 
Style Transfer (F32)
100% 103400
136.0 IPS
 
Style Transfer (F16)
100% 76779
101.0 IPS
 
Style Transfer (I8)
98% 86817
114.2 IPS
 
Image Super-Resolution (F32)
100% 20132
719.0 IPS
 
Image Super-Resolution (F16)
100% 16145
576.6 IPS
 
Image Super-Resolution (I8)
99% 11852
423.3 IPS
 
Text Classification (F32)
100% 1466
2.11 KIPS
 
Text Classification (F16)
100% 1453
2.09 KIPS
 
Text Classification (I8)
98% 1029
1.48 KIPS
 
Machine Translation (F32)
100% 2873
52.9 IPS
 
Machine Translation (F16)
100% 2869
52.8 IPS
 
Machine Translation (I8)
70% 1711
31.5 IPS
 

Compare

Set Baseline Geekbench 6 now available