Geekbench ML Score

9699
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 08:49 AM
Views 3

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% 4907
918.3 IPS
 
Image Classification (F16)
100% 4999
935.4 IPS
 
Image Classification (I8)
100% 4484
839.1 IPS
 
Image Segmentation (F32)
100% 5638
94.2 IPS
 
Image Segmentation (F16)
100% 5424
90.6 IPS
 
Image Segmentation (I8)
98% 4906
81.9 IPS
 
Pose Estimation (F32)
100% 44926
54.4 IPS
 
Pose Estimation (F16)
100% 50965
61.7 IPS
 
Pose Estimation (I8)
100% 39879
48.3 IPS
 
Object Detection (F32)
100% 4464
333.3 IPS
 
Object Detection (F16)
100% 3738
279.1 IPS
 
Object Detection (I8)
61% 3967
296.1 IPS
 
Face Detection (F32)
100% 13573
161.4 IPS
 
Face Detection (F16)
100% 13512
160.7 IPS
 
Face Detection (I8)
89% 11177
132.9 IPS
 
Depth Estimation (F32)
100% 26357
204.4 IPS
 
Depth Estimation (F16)
100% 26110
202.5 IPS
 
Depth Estimation (I8)
95% 23335
181.0 IPS
 
Style Transfer (F32)
100% 107155
141.0 IPS
 
Style Transfer (F16)
100% 73848
97.1 IPS
 
Style Transfer (I8)
98% 78953
103.9 IPS
 
Image Super-Resolution (F32)
100% 19786
706.6 IPS
 
Image Super-Resolution (F16)
100% 16565
591.6 IPS
 
Image Super-Resolution (I8)
99% 12240
437.1 IPS
 
Text Classification (F32)
100% 1629
2.34 KIPS
 
Text Classification (F16)
100% 1802
2.59 KIPS
 
Text Classification (I8)
98% 1260
1.81 KIPS
 
Machine Translation (F32)
100% 2803
51.6 IPS
 
Machine Translation (F16)
100% 2792
51.4 IPS
 
Machine Translation (I8)
70% 1679
30.9 IPS
 

Compare

Set Baseline Geekbench 6 now available