Geekbench ML Score

9532
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 17 2024 04:57 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 83DE
Motherboard LENOVO LNVNB161216
Power PlanLegion Quiet Mode
CPU Information
Name Intel Core i9-14900HX
Topology 1 Processor, 24 Cores, 32 Threads
Identifier GenuineIntel Family 6 Model 183 Stepping 1
Base Frequency 2.20 GHz
Cluster 18 Cores
Cluster 216 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache2.00 MB x 4
L3 Cache36.0 MB x 1
Memory Information
Size 96.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4090 Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4697
879.0 IPS
 
Image Classification (F16)
100% 5188
970.7 IPS
 
Image Classification (I8)
100% 3830
716.8 IPS
 
Image Segmentation (F32)
100% 7769
129.7 IPS
 
Image Segmentation (F16)
100% 7589
126.7 IPS
 
Image Segmentation (I8)
98% 7101
118.6 IPS
 
Pose Estimation (F32)
100% 90012
109.0 IPS
 
Pose Estimation (F16)
100% 86513
104.8 IPS
 
Pose Estimation (I8)
100% 76965
93.2 IPS
 
Object Detection (F32)
100% 2898
216.4 IPS
 
Object Detection (F16)
100% 2912
217.4 IPS
 
Object Detection (I8)
56% 2679
200.0 IPS
 
Face Detection (F32)
100% 15397
183.1 IPS
 
Face Detection (F16)
100% 15494
184.2 IPS
 
Face Detection (I8)
89% 13153
156.4 IPS
 
Depth Estimation (F32)
100% 25609
198.6 IPS
 
Depth Estimation (F16)
100% 25743
199.6 IPS
 
Depth Estimation (I8)
94% 20925
162.3 IPS
 
Style Transfer (F32)
100% 123745
162.8 IPS
 
Style Transfer (F16)
100% 124362
163.6 IPS
 
Style Transfer (I8)
98% 108855
143.2 IPS
 
Image Super-Resolution (F32)
100% 14865
530.9 IPS
 
Image Super-Resolution (F16)
100% 15042
537.2 IPS
 
Image Super-Resolution (I8)
99% 12078
431.3 IPS
 
Text Classification (F32)
100% 1150
1.65 KIPS
 
Text Classification (F16)
100% 1184
1.70 KIPS
 
Text Classification (I8)
98% 745
1.07 KIPS
 
Machine Translation (F32)
100% 1638
30.1 IPS
 
Machine Translation (F16)
100% 1510
27.8 IPS
 
Machine Translation (I8)
70% 913
16.8 IPS
 

Compare

Set Baseline Geekbench 6 now available