Geekbench ML Score

2078
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Linux AVX2

Result Information

Upload Date January 10 2024 11:46 PM
Views 3

System Information

System Information
Operating System Pop!_OS 22.04 LTS
Model ASUS System Product Name
Motherboard ASUSTeK COMPUTER INC. PRIME Z790-A WIFI
CPU Information
Name Intel Core i5-12600K
Topology 1 Processor, 10 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 151 Stepping 2
Base Frequency 4.90 GHz
Cluster 10 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache48.0 KB x 8
L2 Cache1.25 MB x 2
L3 Cache20.0 MB x 1
Memory Information
Size 62.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1686
315.4 IPS
 
Image Classification (F16)
100% 1684
315.0 IPS
 
Image Classification (I8)
99% 1010
189.0 IPS
 
Image Segmentation (F32)
100% 2124
35.5 IPS
 
Image Segmentation (F16)
100% 2099
35.1 IPS
 
Image Segmentation (I8)
98% 1032
17.2 IPS
 
Pose Estimation (F32)
100% 3127
3.79 IPS
 
Pose Estimation (F16)
100% 3122
3.78 IPS
 
Pose Estimation (I8)
100% 2794
3.38 IPS
 
Object Detection (F32)
100% 1813
135.4 IPS
 
Object Detection (F16)
100% 1784
133.2 IPS
 
Object Detection (I8)
65% 1160
86.6 IPS
 
Face Detection (F32)
100% 3113
37.0 IPS
 
Face Detection (F16)
100% 3121
37.1 IPS
 
Face Detection (I8)
87% 2303
27.4 IPS
 
Depth Estimation (F32)
100% 3051
23.7 IPS
 
Depth Estimation (F16)
100% 3032
23.5 IPS
 
Depth Estimation (I8)
95% 2312
17.9 IPS
 
Style Transfer (F32)
100% 4213
5.54 IPS
 
Style Transfer (F16)
100% 4255
5.60 IPS
 
Style Transfer (I8)
98% 5624
7.40 IPS
 
Image Super-Resolution (F32)
100% 2148
76.7 IPS
 
Image Super-Resolution (F16)
100% 2131
76.1 IPS
 
Image Super-Resolution (I8)
98% 1499
53.5 IPS
 
Text Classification (F32)
100% 1332
1.91 KIPS
 
Text Classification (F16)
100% 1333
1.92 KIPS
 
Text Classification (I8)
92% 598
858.8 IPS
 
Machine Translation (F32)
100% 2897
53.3 IPS
 
Machine Translation (F16)
100% 2874
52.9 IPS
 
Machine Translation (I8)
62% 861
15.8 IPS
 

Compare

Set Baseline Geekbench 6 now available