TensorFlow Lite
This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time.
To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark tensorflow-lite.
Project Site
tensorflow.orgSource Repository
github.comTest Created
23 August 2020Last Updated
19 May 2022Test Maintainer
Michael LarabelTest Type
SystemAverage Install Time
9 SecondsAverage Run Time
4 Minutes, 53 SecondsAccolades
10k+ DownloadsSupported Platforms
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
*** Test profile page view reporting began March 2021.
Data updated weekly as of 21 April 2024.
Suites Using This Test
Performance Metrics
Analyze Test Configuration:TensorFlow Lite 2020-08-23
Model: Inception V4
OpenBenchmarking.org metrics for this test profile configuration based on 1,440 public results since 23 August 2020 with the latest data as of 3 October 2023.
Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.
Based on OpenBenchmarking.org data, the selected test / test configuration (TensorFlow Lite 2020-08-23 - Model: Inception V4) has an average run-time of 7 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.
Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.2%.
Does It Scale Well With Increasing Cores?
Yes, based on the automated analysis of the collected public benchmark data, this test / test settings does generally scale well with increasing CPU core counts. Data based on publicly available results for this test / test settings, separated by vendor, result divided by the reference CPU clock speed, grouped by matching physical CPU core count, and normalized against the smallest core count tested from each vendor for each CPU having a sufficient number of test samples and statistically significant data.
Notable Instruction Set Usage
Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).
This test profile binary relies on the shared libraries libm.so.6, libpthread.so.0, libdl.so.2, librt.so.1, libc.so.6.
Tested CPU Architectures
This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.