Geekbench ML Score

616
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 08 2023 04:08 PM
Views 1

System Information

System Information
Operating System Android 14
Model Google Pixel Fold
Model IDGoogle Pixel Fold
Motherboard felix
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.35 GHz
Cluster 32 Cores @ 2.85 GHz
Memory Information
Size 11.19 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 347
64.9 IPS
 
Image Classification (F16)
100% 314
58.7 IPS
 
Image Classification (I8)
97% 632
118.3 IPS
 
Image Segmentation (F32)
100% 406
6.78 IPS
 
Image Segmentation (F16)
100% 406
6.77 IPS
 
Image Segmentation (I8)
98% 639
10.7 IPS
 
Pose Estimation (F32)
100% 711
0.86 IPS
 
Pose Estimation (F16)
100% 696
0.84 IPS
 
Pose Estimation (I8)
100% 3242
3.93 IPS
 
Object Detection (F32)
100% 263
19.6 IPS
 
Object Detection (F16)
100% 250
18.7 IPS
 
Object Detection (I8)
61% 519
38.7 IPS
 
Face Detection (F32)
100% 629
7.48 IPS
 
Face Detection (F16)
100% 609
7.24 IPS
 
Face Detection (I8)
86% 1458
17.3 IPS
 
Depth Estimation (F32)
100% 676
5.24 IPS
 
Depth Estimation (F16)
100% 646
5.01 IPS
 
Depth Estimation (I8)
95% 1221
9.47 IPS
 
Style Transfer (F32)
100% 1121
1.47 IPS
 
Style Transfer (F16)
100% 1079
1.42 IPS
 
Style Transfer (I8)
98% 2115
2.78 IPS
 
Image Super-Resolution (F32)
100% 407
14.5 IPS
 
Image Super-Resolution (F16)
100% 404
14.4 IPS
 
Image Super-Resolution (I8)
98% 1320
47.1 IPS
 
Text Classification (F32)
100% 370
531.8 IPS
 
Text Classification (F16)
100% 406
583.6 IPS
 
Text Classification (I8)
92% 338
486.4 IPS
 
Machine Translation (F32)
100% 767
14.1 IPS
 
Machine Translation (F16)
100% 616
11.3 IPS
 
Machine Translation (I8)
64% 311
5.73 IPS
 

Compare

Set Baseline Geekbench 6 now available