Geekbench ML Score

1829
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Linux AVX2

Result Information

Upload Date September 27 2024 07:33 AM
Views 2

System Information

System Information
Operating System Linux Mint 22
Model Gigabyte Technology Co., Ltd. B650 AORUS ELITE AX V2
Motherboard Gigabyte Technology Co., Ltd. B650 AORUS ELITE AX V2
CPU Information
Name AMD Ryzen 7 9700X 8-Core Processor
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 26 Model 68 Stepping 0
Base Frequency 4.00 GHz
Cluster 10 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache48.0 KB x 8
L2 Cache1.00 MB x 8
L3 Cache32.0 MB x 1
Memory Information
Size 30.96 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1518
284.1 IPS
 
Image Classification (F16)
100% 1517
284.0 IPS
 
Image Classification (I8)
99% 884
165.3 IPS
 
Image Segmentation (F32)
100% 1955
32.7 IPS
 
Image Segmentation (F16)
100% 1957
32.7 IPS
 
Image Segmentation (I8)
98% 746
12.5 IPS
 
Pose Estimation (F32)
100% 2584
3.13 IPS
 
Pose Estimation (F16)
100% 2587
3.13 IPS
 
Pose Estimation (I8)
100% 2410
2.92 IPS
 
Object Detection (F32)
100% 1203
89.8 IPS
 
Object Detection (F16)
100% 1194
89.1 IPS
 
Object Detection (I8)
65% 828
61.8 IPS
 
Face Detection (F32)
100% 3457
41.1 IPS
 
Face Detection (F16)
100% 3466
41.2 IPS
 
Face Detection (I8)
87% 1815
21.6 IPS
 
Depth Estimation (F32)
100% 2879
22.3 IPS
 
Depth Estimation (F16)
100% 2877
22.3 IPS
 
Depth Estimation (I8)
95% 1838
14.3 IPS
 
Style Transfer (F32)
100% 3861
5.08 IPS
 
Style Transfer (F16)
100% 3861
5.08 IPS
 
Style Transfer (I8)
98% 4679
6.16 IPS
 
Image Super-Resolution (F32)
100% 1717
61.3 IPS
 
Image Super-Resolution (F16)
100% 1726
61.6 IPS
 
Image Super-Resolution (I8)
98% 1242
44.3 IPS
 
Text Classification (F32)
100% 1572
2.26 KIPS
 
Text Classification (F16)
100% 1576
2.27 KIPS
 
Text Classification (I8)
92% 522
750.3 IPS
 
Machine Translation (F32)
100% 3038
55.9 IPS
 
Machine Translation (F16)
100% 3062
56.4 IPS
 
Machine Translation (I8)
62% 654
12.0 IPS
 

Compare

Set Baseline Geekbench 6 now available