Geekbench ML Score

697
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 07 2024 07:24 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model System manufacturer System Product Name
Motherboard ASUSTeK COMPUTER INC. B250 MINING EXPERT
Power PlanBalanced
CPU Information
Name Intel Core i3-7350K
Topology 1 Processor, 2 Cores, 4 Threads
Identifier GenuineIntel Family 6 Model 158 Stepping 9
Base Frequency 4.20 GHz
Cluster 12 Cores
L1 Instruction Cache32.0 KB x 2
L1 Data Cache32.0 KB x 2
L2 Cache256 KB x 2
L3 Cache4.00 MB x 1
Memory Information
Size 8.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 410
76.7 IPS
 
Image Classification (F16)
100% 341
63.8 IPS
 
Image Classification (I8)
97% 618
115.6 IPS
 
Image Segmentation (F32)
100% 270
4.50 IPS
 
Image Segmentation (F16)
100% 317
5.29 IPS
 
Image Segmentation (I8)
97% 439
7.33 IPS
 
Pose Estimation (F32)
100% 996
1.21 IPS
 
Pose Estimation (F16)
100% 1227
1.49 IPS
 
Pose Estimation (I8)
100% 1585
1.92 IPS
 
Object Detection (F32)
100% 306
22.8 IPS
 
Object Detection (F16)
100% 276
20.6 IPS
 
Object Detection (I8)
60% 437
32.6 IPS
 
Face Detection (F32)
100% 553
6.58 IPS
 
Face Detection (F16)
100% 578
6.87 IPS
 
Face Detection (I8)
87% 926
11.0 IPS
 
Depth Estimation (F32)
100% 1333
10.3 IPS
 
Depth Estimation (F16)
100% 1159
8.98 IPS
 
Depth Estimation (I8)
74% 1792
13.9 IPS
 
Style Transfer (F32)
100% 2344
3.08 IPS
 
Style Transfer (F16)
100% 2934
3.86 IPS
 
Style Transfer (I8)
85% 3165
4.16 IPS
 
Image Super-Resolution (F32)
100% 528
18.9 IPS
 
Image Super-Resolution (F16)
100% 672
24.0 IPS
 
Image Super-Resolution (I8)
97% 997
35.6 IPS
 
Text Classification (F32)
100% 443
636.0 IPS
 
Text Classification (F16)
100% 424
609.6 IPS
 
Text Classification (I8)
94% 265
380.5 IPS
 
Machine Translation (F32)
100% 664
12.2 IPS
 
Machine Translation (F16)
100% 664
12.2 IPS
 
Machine Translation (I8)
67% 617
11.4 IPS
 

Compare

Set Baseline Geekbench 6 now available