Geekbench ML Score

5536
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date December 12 2024 01:43 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model Acer Swift SF14-51
Motherboard LNL Icefish_LNV
Power PlanAcer
CPU Information
Name Intel(R) Core(TM) Ultra 7 258V
Topology 1 Processor, 8 Cores
Identifier GenuineIntel Family 6 Model 189 Stepping 1
Base Frequency 2.20 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache48.0 KB x 4
L2 Cache2.50 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (16GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3349
626.7 IPS
 
Image Classification (F16)
100% 2804
524.8 IPS
 
Image Classification (I8)
100% 2099
392.8 IPS
 
Image Segmentation (F32)
100% 6167
103.0 IPS
 
Image Segmentation (F16)
100% 6063
101.3 IPS
 
Image Segmentation (I8)
98% 4567
76.3 IPS
 
Pose Estimation (F32)
100% 21438
26.0 IPS
 
Pose Estimation (F16)
100% 19732
23.9 IPS
 
Pose Estimation (I8)
100% 16149
19.6 IPS
 
Object Detection (F32)
100% 2942
219.7 IPS
 
Object Detection (F16)
100% 2947
220.0 IPS
 
Object Detection (I8)
61% 2594
193.6 IPS
 
Face Detection (F32)
100% 8112
96.5 IPS
 
Face Detection (F16)
100% 7928
94.3 IPS
 
Face Detection (I8)
89% 5477
65.1 IPS
 
Depth Estimation (F32)
100% 18518
143.6 IPS
 
Depth Estimation (F16)
100% 18029
139.8 IPS
 
Depth Estimation (I8)
94% 13505
104.7 IPS
 
Style Transfer (F32)
100% 45984
60.5 IPS
 
Style Transfer (F16)
100% 45068
59.3 IPS
 
Style Transfer (I8)
98% 43079
56.7 IPS
 
Image Super-Resolution (F32)
100% 7803
278.7 IPS
 
Image Super-Resolution (F16)
100% 8695
310.5 IPS
 
Image Super-Resolution (I8)
99% 4991
178.2 IPS
 
Text Classification (F32)
100% 930
1.34 KIPS
 
Text Classification (F16)
100% 695
998.9 IPS
 
Text Classification (I8)
98% 561
806.1 IPS
 
Machine Translation (F32)
100% 1619
29.8 IPS
 
Machine Translation (F16)
100% 1555
28.6 IPS
 
Machine Translation (I8)
70% 874
16.1 IPS
 

Compare

Set Baseline Geekbench 6 now available