Geekbench ML Score

1982
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Linux AVX2

Result Information

Upload Date June 10 2025 10:17 PM
Views 6

System Information

System Information
Operating System Gentoo Linux
Model Micro-Star International Co., Ltd. MS-7C84
Motherboard Micro-Star International Co., Ltd. MAG X570 TOMAHAWK WIFI (MS-7C84)
CPU Information
Name AMD Ryzen 9 5950X
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 25 Model 33 Stepping 0
Base Frequency 5.08 GHz
Cluster 10 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache32.0 KB x 16
L2 Cache512 KB x 16
L3 Cache32.0 MB x 2
Memory Information
Size 125.73 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1484
277.7 IPS
 
Image Classification (F16)
100% 1479
276.7 IPS
 
Image Classification (I8)
99% 1142
213.8 IPS
 
Image Segmentation (F32)
100% 2243
37.5 IPS
 
Image Segmentation (F16)
100% 2231
37.3 IPS
 
Image Segmentation (I8)
98% 1208
20.2 IPS
 
Pose Estimation (F32)
100% 2475
3.00 IPS
 
Pose Estimation (F16)
100% 2508
3.04 IPS
 
Pose Estimation (I8)
100% 4072
4.93 IPS
 
Object Detection (F32)
100% 1603
119.7 IPS
 
Object Detection (F16)
100% 1614
120.5 IPS
 
Object Detection (I8)
65% 1498
111.9 IPS
 
Face Detection (F32)
100% 2578
30.6 IPS
 
Face Detection (F16)
100% 2573
30.6 IPS
 
Face Detection (I8)
87% 2589
30.8 IPS
 
Depth Estimation (F32)
100% 2379
18.5 IPS
 
Depth Estimation (F16)
100% 2334
18.1 IPS
 
Depth Estimation (I8)
95% 2604
20.2 IPS
 
Style Transfer (F32)
100% 2690
3.54 IPS
 
Style Transfer (F16)
100% 2702
3.55 IPS
 
Style Transfer (I8)
98% 6072
7.99 IPS
 
Image Super-Resolution (F32)
100% 1629
58.2 IPS
 
Image Super-Resolution (F16)
100% 1626
58.1 IPS
 
Image Super-Resolution (I8)
98% 1881
67.2 IPS
 
Text Classification (F32)
100% 1289
1.85 KIPS
 
Text Classification (F16)
100% 1396
2.01 KIPS
 
Text Classification (I8)
92% 685
983.8 IPS
 
Machine Translation (F32)
100% 2970
54.7 IPS
 
Machine Translation (F16)
100% 2978
54.8 IPS
 
Machine Translation (I8)
62% 936
17.2 IPS
 

Compare

Set Baseline Geekbench 6 now available