Geekbench ML Score

316
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 04:46 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone X
Model IDiPhone10,6
Motherboard D221AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.76 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 215
23.1 IPS
 
Image Classification (F16)
100% 235
25.2 IPS
 
Image Classification (I8)
81% 306
32.8 IPS
 
Image Segmentation (F32)
100% 385
2.38 IPS
 
Image Segmentation (F16)
100% 386
2.38 IPS
 
Image Segmentation (I8)
89% 671
4.14 IPS
 
Pose Estimation (F32)
100% 86
0.35 IPS
 
Pose Estimation (F16)
100% 86
0.35 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 351
12.3 IPS
 
Object Detection (F16)
100% 350
12.3 IPS
 
Object Detection (I8)
52% 487
17.1 IPS
 
Face Detection (F32)
100% 436
5.01 IPS
 
Face Detection (F16)
100% 436
5.01 IPS
 
Face Detection (I8)
75% 466
5.36 IPS
 
Text Classification (F32)
100% 433
171.3 IPS
 
Text Classification (F16)
100% 432
170.8 IPS
 
Machine Translation (F32)
100% 481
74.1 IPS
 
Machine Translation (F16)
100% 475
73.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download