Geekbench ML Score

401
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date June 29 2024 04:36 AM
Views 1

System Information

System Information
Operating System Android 14
Model HEADWOLF F5
Model IDHEADWOLF F5
Motherboard HEADWOLF
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 7.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 192
35.9 IPS
 
Image Classification (F16)
100% 187
35.0 IPS
 
Image Classification (I8)
97% 329
61.5 IPS
 
Image Segmentation (F32)
100% 294
4.91 IPS
 
Image Segmentation (F16)
100% 294
4.91 IPS
 
Image Segmentation (I8)
98% 415
6.93 IPS
 
Pose Estimation (F32)
100% 395
0.48 IPS
 
Pose Estimation (F16)
100% 405
0.49 IPS
 
Pose Estimation (I8)
100% 1789
2.17 IPS
 
Object Detection (F32)
100% 226
16.9 IPS
 
Object Detection (F16)
100% 222
16.6 IPS
 
Object Detection (I8)
61% 394
29.4 IPS
 
Face Detection (F32)
100% 438
5.21 IPS
 
Face Detection (F16)
100% 436
5.18 IPS
 
Face Detection (I8)
86% 893
10.6 IPS
 
Depth Estimation (F32)
100% 429
3.32 IPS
 
Depth Estimation (F16)
100% 418
3.24 IPS
 
Depth Estimation (I8)
95% 920
7.13 IPS
 
Style Transfer (F32)
100% 661
0.87 IPS
 
Style Transfer (F16)
100% 661
0.87 IPS
 
Style Transfer (I8)
98% 2039
2.68 IPS
 
Image Super-Resolution (F32)
100% 244
8.70 IPS
 
Image Super-Resolution (F16)
100% 244
8.72 IPS
 
Image Super-Resolution (I8)
98% 675
24.1 IPS
 
Text Classification (F32)
100% 226
324.8 IPS
 
Text Classification (F16)
100% 236
338.8 IPS
 
Text Classification (I8)
92% 183
263.7 IPS
 
Machine Translation (F32)
100% 457
8.41 IPS
 
Machine Translation (F16)
100% 456
8.38 IPS
 
Machine Translation (I8)
64% 258
4.74 IPS
 

Compare

Set Baseline Geekbench 6 now available