Geekbench ML Score

9531
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 08:48 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% 5038
942.8 IPS
 
Image Classification (F16)
100% 5020
939.3 IPS
 
Image Classification (I8)
100% 4484
839.1 IPS
 
Image Segmentation (F32)
100% 5573
93.1 IPS
 
Image Segmentation (F16)
100% 5420
90.5 IPS
 
Image Segmentation (I8)
98% 4929
82.3 IPS
 
Pose Estimation (F32)
100% 44769
54.2 IPS
 
Pose Estimation (F16)
100% 58263
70.6 IPS
 
Pose Estimation (I8)
100% 39469
47.8 IPS
 
Object Detection (F32)
100% 4524
337.8 IPS
 
Object Detection (F16)
100% 3790
283.0 IPS
 
Object Detection (I8)
61% 4204
313.9 IPS
 
Face Detection (F32)
100% 13649
162.3 IPS
 
Face Detection (F16)
100% 13469
160.2 IPS
 
Face Detection (I8)
89% 10994
130.7 IPS
 
Depth Estimation (F32)
100% 26542
205.8 IPS
 
Depth Estimation (F16)
100% 19811
153.6 IPS
 
Depth Estimation (I8)
95% 20564
159.5 IPS
 
Style Transfer (F32)
100% 105137
138.3 IPS
 
Style Transfer (F16)
100% 73277
96.4 IPS
 
Style Transfer (I8)
98% 67375
88.6 IPS
 
Image Super-Resolution (F32)
100% 16776
599.1 IPS
 
Image Super-Resolution (F16)
100% 16273
581.2 IPS
 
Image Super-Resolution (I8)
99% 12151
434.0 IPS
 
Text Classification (F32)
100% 1590
2.29 KIPS
 
Text Classification (F16)
100% 1875
2.69 KIPS
 
Text Classification (I8)
98% 1281
1.84 KIPS
 
Machine Translation (F32)
100% 2801
51.5 IPS
 
Machine Translation (F16)
100% 2782
51.2 IPS
 
Machine Translation (I8)
70% 1691
31.1 IPS
 

Compare

Set Baseline Geekbench 6 now available