Geekbench ML Score

1595
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Linux AVX2

Result Information

User oleker
Upload Date July 25 2024 11:46 PM
Views 1

System Information

System Information
Operating System Debian GNU/Linux 12 (bookworm)
Model Micro Computer (HK) Tech Limited Venus Series
Motherboard Shenzhen Meigao Electronic Equipment Co.,Ltd AHWSA
CPU Information
Name Intel Core i9-12900H
Topology 1 Processor, 14 Cores, 20 Threads
Identifier GenuineIntel Family 6 Model 154 Stepping 3
Base Frequency 4.90 GHz
Cluster 10 Cores
L1 Instruction Cache64.0 KB x 10
L1 Data Cache32.0 KB x 10
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 62.53 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1415
264.9 IPS
 
Image Classification (F16)
100% 1396
261.2 IPS
 
Image Classification (I8)
99% 850
159.1 IPS
 
Image Segmentation (F32)
100% 1803
30.1 IPS
 
Image Segmentation (F16)
100% 1824
30.5 IPS
 
Image Segmentation (I8)
98% 795
13.3 IPS
 
Pose Estimation (F32)
100% 2322
2.81 IPS
 
Pose Estimation (F16)
100% 2309
2.80 IPS
 
Pose Estimation (I8)
100% 2392
2.90 IPS
 
Object Detection (F32)
100% 1473
110.0 IPS
 
Object Detection (F16)
100% 1528
114.1 IPS
 
Object Detection (I8)
65% 982
73.3 IPS
 
Face Detection (F32)
100% 2382
28.3 IPS
 
Face Detection (F16)
100% 2375
28.2 IPS
 
Face Detection (I8)
87% 1824
21.7 IPS
 
Depth Estimation (F32)
100% 2182
16.9 IPS
 
Depth Estimation (F16)
100% 2158
16.7 IPS
 
Depth Estimation (I8)
95% 1802
14.0 IPS
 
Style Transfer (F32)
100% 2712
3.57 IPS
 
Style Transfer (F16)
100% 2702
3.55 IPS
 
Style Transfer (I8)
98% 4273
5.62 IPS
 
Image Super-Resolution (F32)
100% 1727
61.7 IPS
 
Image Super-Resolution (F16)
100% 1713
61.2 IPS
 
Image Super-Resolution (I8)
98% 1262
45.1 IPS
 
Text Classification (F32)
100% 1085
1.56 KIPS
 
Text Classification (F16)
100% 1153
1.66 KIPS
 
Text Classification (I8)
92% 341
489.8 IPS
 
Machine Translation (F32)
100% 1905
35.1 IPS
 
Machine Translation (F16)
100% 1934
35.6 IPS
 
Machine Translation (I8)
62% 607
11.2 IPS
 

Compare

Set Baseline Geekbench 6 now available