Geekbench ML Score

9765
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 03:07 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% 5073
949.4 IPS
 
Image Classification (F16)
100% 4996
934.9 IPS
 
Image Classification (I8)
100% 4469
836.2 IPS
 
Image Segmentation (F32)
100% 5482
91.6 IPS
 
Image Segmentation (F16)
100% 5425
90.6 IPS
 
Image Segmentation (I8)
98% 4964
82.9 IPS
 
Pose Estimation (F32)
100% 44602
54.0 IPS
 
Pose Estimation (F16)
100% 57928
70.1 IPS
 
Pose Estimation (I8)
100% 53089
64.3 IPS
 
Object Detection (F32)
100% 4582
342.1 IPS
 
Object Detection (F16)
100% 3721
277.8 IPS
 
Object Detection (I8)
61% 3581
267.4 IPS
 
Face Detection (F32)
100% 13552
161.1 IPS
 
Face Detection (F16)
100% 13617
161.9 IPS
 
Face Detection (I8)
89% 11296
134.3 IPS
 
Depth Estimation (F32)
100% 26551
205.9 IPS
 
Depth Estimation (F16)
100% 26572
206.1 IPS
 
Depth Estimation (I8)
95% 17017
132.0 IPS
 
Style Transfer (F32)
100% 106928
140.7 IPS
 
Style Transfer (F16)
100% 83961
110.4 IPS
 
Style Transfer (I8)
98% 82870
109.0 IPS
 
Image Super-Resolution (F32)
100% 19898
710.6 IPS
 
Image Super-Resolution (F16)
100% 16567
591.7 IPS
 
Image Super-Resolution (I8)
99% 12203
435.8 IPS
 
Text Classification (F32)
100% 1621
2.33 KIPS
 
Text Classification (F16)
100% 1764
2.53 KIPS
 
Text Classification (I8)
98% 1236
1.78 KIPS
 
Machine Translation (F32)
100% 2803
51.6 IPS
 
Machine Translation (F16)
100% 2790
51.3 IPS
 
Machine Translation (I8)
70% 1693
31.2 IPS
 

Compare

Set Baseline Geekbench 6 now available