tflite-runtime
TensorFlow Lite is for mobile and embedded devices.
Decision gist · record as of 2026-08-14
Yes, if you have a pre-converted .tflite model and need to run inference on mobile or embedded devices. The package is stable, lightweight, and carries no known vulnerabilities. However, the dormant maintenance status means no recent updates or security patches; verify compatibility with your target model format and hardware before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a pre-converted TensorFlow Lite model (.tflite file); numpy is a runtime dependency.
- Medium install friction due to platform-specific wheels for x86_64, aarch64, and armv7l architectures across Python 3.8–3.11.
- Package is dormant (last release 1046 days ago), but carries Production/Stable status and no known vulnerabilities.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most deployment scenarios.
last release 2023-10-03 (1046 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 120,678 downloads/mo, #12,013 on PyPI
Alternatives
Verify before relying
pip install tflite-runtime
import tflite_runtime.interpreter as tflite
interpreter = tflite.Interpreter(model_path='model.tflite')
interpreter.allocate_tensors()
output = interpreter.get_tensor(interpreter.get_output_details()[0]['index'])- Whether dormant status affects compatibility with current model formats or ecosystem changes.
- Performance characteristics compared to other edge inference runtimes on specific hardware.
- Support timeline and security patch policy for the dormant package.
- Whether the package works on Python versions beyond 3.11.
What it is and what it does
TensorFlow Lite runtime is the official inference engine for running pre-trained machine learning models on mobile and embedded devices. It is designed to execute models with minimal latency and a small footprint, supporting Android, iOS, and other operating systems. The package provides Python bindings to load and run .tflite model files, making it suitable for edge deployment scenarios where full TensorFlow would be too heavy.
The package depends only on numpy and ships as platform-specific wheels for common architectures (x86_64, aarch64, armv7l) across Python 3.8–3.11. It is classified as Production/Stable and carries no known security vulnerabilities, though the package has been dormant since its last release on 2023-10-03.
Use it for
- Run pre-trained image classification or object detection models on Raspberry Pi or ARM-based edge devices.
- Deploy real-time inference pipelines on mobile devices without the overhead of the full TensorFlow library.
- Execute quantized or pruned models for resource-constrained IoT and embedded systems.
- Integrate lightweight neural networks into Python applications on ARM architectures (aarch64, armv7l).
- Prototype and test model inference performance on edge hardware before production deployment.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you have a pre-converted .tflite model and need to run inference on mobile or embedded devices.
The package is stable, lightweight, and carries no known vulnerabilities. However, the dormant maintenance status means no recent updates or security patches; verify compatibility with your target model format and hardware before committing to production use.
Install
tflite-runtime on PyPI
Before you install
Medium install friction due to platform-specific wheels for x86_64, aarch64, and armv7l architectures across Python 3.8–3.11. Package is dormant (last release 1046 days ago), but carries Production/Stable status and no known vulnerabilities.
Requires a pre-converted TensorFlow Lite model (.tflite file); numpy is a runtime dependency.
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most deployment scenarios.
Quickstart
pip install tflite-runtime
import tflite_runtime.interpreter as tflite
interpreter = tflite.Interpreter(model_path='model.tflite')
interpreter.allocate_tensors()
output = interpreter.get_tensor(interpreter.get_output_details()[0]['index'])Verify before relying
- Whether dormant status affects compatibility with current model formats or ecosystem changes.
- Performance characteristics compared to other edge inference runtimes on specific hardware.
- Support timeline and security patch policy for the dormant package.
- Whether the package works on Python versions beyond 3.11.
Package facts
| License | Apache 2.0 permissive |
| Python support | Not specified |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagenumpy |
| Maintenance | Dormant 1,046 days since the last release |
| First released | |
| Downloads | 120,678 / month, #12,013 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: tflite_runtime-2.14.0-cp310-cp310-manylinux2014_x86_64.whl; tflite_runtime-2.14.0-cp310-cp310-manylinux_2_34_aarch64.whl; tflite_runtime-2.14.0-cp310-cp310-manylinux_2_34_armv7l.whl; tflite_runtime-2.14.0-cp311-cp311-manylinux2014_x86_64.whl; tflite_runtime-2.14.0-cp311-cp311-manylinux_2_34_aarch64.whl; tflite_runtime-2.14.0-cp311-cp311-manylinux_2_34_armv7l.whl; tflite_runtime-2.14.0-cp38-cp38-manylinux2014_x86_64.whl; tflite_runtime-2.14.0-cp38-cp38-manylinux_2_34_aarch64.whl; tflite_runtime-2.14.0-cp38-cp38-manylinux_2_34_armv7l.whl; tflite_runtime-2.14.0-cp39-cp39-manylinux2014_x86_64.whl; tflite_runtime-2.14.0-cp39-cp39-manylinux_2_34_aarch64.whl; tflite_runtime-2.14.0-cp39-cp39-manylinux_2_34_armv7l.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “tensorflow lite inference”
- tflite-runtimeTensorFlow Lite runtime enables on-device machine learning inference…
- ai-edge-litertai-edge-litert runs machine learning models on mobile and embedded…
- tfliteParses TensorFlow Lite (*.tflite) model files and provides a Python…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also ai-edge-litert · executorch · mnn · mobly · tflite · litert-converter · ai-edge-litert-nightly · mediapipe · litert-torch · onnxruntime-genai