Geekbench ML Score

9683
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 07:14 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% 4926
921.9 IPS
 
Image Classification (F16)
100% 4847
907.1 IPS
 
Image Classification (I8)
100% 4351
814.2 IPS
 
Image Segmentation (F32)
100% 7013
117.1 IPS
 
Image Segmentation (F16)
100% 5468
91.3 IPS
 
Image Segmentation (I8)
98% 4998
83.5 IPS
 
Pose Estimation (F32)
100% 44863
54.3 IPS
 
Pose Estimation (F16)
100% 58457
70.8 IPS
 
Pose Estimation (I8)
100% 39808
48.2 IPS
 
Object Detection (F32)
100% 4695
350.5 IPS
 
Object Detection (F16)
100% 4680
349.4 IPS
 
Object Detection (I8)
61% 3528
263.4 IPS
 
Face Detection (F32)
100% 13668
162.5 IPS
 
Face Detection (F16)
100% 13371
159.0 IPS
 
Face Detection (I8)
89% 11375
135.2 IPS
 
Depth Estimation (F32)
100% 26199
203.2 IPS
 
Depth Estimation (F16)
100% 26211
203.3 IPS
 
Depth Estimation (I8)
95% 22566
175.0 IPS
 
Style Transfer (F32)
100% 105322
138.5 IPS
 
Style Transfer (F16)
100% 73010
96.0 IPS
 
Style Transfer (I8)
98% 66929
88.0 IPS
 
Image Super-Resolution (F32)
100% 17004
607.3 IPS
 
Image Super-Resolution (F16)
100% 16254
580.5 IPS
 
Image Super-Resolution (I8)
99% 12027
429.5 IPS
 
Text Classification (F32)
100% 1515
2.18 KIPS
 
Text Classification (F16)
100% 1742
2.50 KIPS
 
Text Classification (I8)
98% 1168
1.68 KIPS
 
Machine Translation (F32)
100% 2863
52.7 IPS
 
Machine Translation (F16)
100% 2857
52.6 IPS
 
Machine Translation (I8)
70% 1703
31.3 IPS
 

Compare

Set Baseline Geekbench 6 now available