Geekbench ML Score

2769
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Linux AVX2

Result Information

Upload Date January 07 2024 09:02 PM
Views 2

System Information

System Information
Operating System Ubuntu 23.10
Model ASUS System Product Name
Motherboard ASUSTeK COMPUTER INC. PRIME H770-PLUS D4
CPU Information
Name Intel Core i9-13900K
Topology 1 Processor, 24 Cores, 32 Threads
Identifier GenuineIntel Family 6 Model 183 Stepping 1
Base Frequency 5.50 GHz
Cluster 10 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache2.00 MB x 4
L3 Cache36.0 MB x 1
Memory Information
Size 62.52 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2263
423.5 IPS
 
Image Classification (F16)
100% 2287
427.9 IPS
 
Image Classification (I8)
99% 1290
241.4 IPS
 
Image Segmentation (F32)
100% 3714
62.0 IPS
 
Image Segmentation (F16)
100% 3698
61.8 IPS
 
Image Segmentation (I8)
98% 1596
26.7 IPS
 
Pose Estimation (F32)
100% 3590
4.35 IPS
 
Pose Estimation (F16)
100% 3576
4.33 IPS
 
Pose Estimation (I8)
100% 5347
6.47 IPS
 
Object Detection (F32)
100% 2839
212.0 IPS
 
Object Detection (F16)
100% 2839
211.9 IPS
 
Object Detection (I8)
65% 1999
149.3 IPS
 
Face Detection (F32)
100% 4254
50.6 IPS
 
Face Detection (F16)
100% 4241
50.4 IPS
 
Face Detection (I8)
87% 3532
42.0 IPS
 
Depth Estimation (F32)
100% 3439
26.7 IPS
 
Depth Estimation (F16)
100% 3424
26.5 IPS
 
Depth Estimation (I8)
95% 3559
27.6 IPS
 
Style Transfer (F32)
100% 3492
4.59 IPS
 
Style Transfer (F16)
100% 3503
4.61 IPS
 
Style Transfer (I8)
98% 8150
10.7 IPS
 
Image Super-Resolution (F32)
100% 2906
103.8 IPS
 
Image Super-Resolution (F16)
100% 3076
109.9 IPS
 
Image Super-Resolution (I8)
98% 2363
84.4 IPS
 
Text Classification (F32)
100% 1582
2.27 KIPS
 
Text Classification (F16)
100% 1397
2.01 KIPS
 
Text Classification (I8)
92% 565
812.0 IPS
 
Machine Translation (F32)
100% 3851
70.9 IPS
 
Machine Translation (F16)
100% 3937
72.4 IPS
 
Machine Translation (I8)
62% 1089
20.0 IPS
 

Compare

Set Baseline Geekbench 6 now available