tflite
Parsing TensorFlow Lite Models (*.tflite) Easily
Decision gist · record as of 2026-08-14
No. The repository is archived and abandoned with no active maintenance. While install friction is low and licensing is permissive, relying on it carries risk: schema definitions may become out of sync with current TFLite versions, and no one will fix compatibility issues. Use only if locked to an older TensorFlow version and need to inspect legacy models.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a matching TensorFlow version to be installed separately; schema definitions may not align with newer TFLite converter versions.
- Low install friction with only two runtime dependencies (flatbuffers and numpy).
- However, the repository is archived and marked abandoned, with no active maintenance since the latest release.
License · maintenance · safety
Apache License 2.0 (permissive) — Licensed under Apache License 2.0 (permissive). No licensing restrictions on use or redistribution.
last release 2025-01-28 (563 days) · last repo commit 2025-01-28 · 102 stars · archived
0 known vulnerabilities (OSV.dev, 2026-08-14) · 123,332 downloads/mo, #11,912 on PyPI
Alternatives
Verify before relying
pip install tflite==2.18.0
import tflite
model = tflite.Model.GetRootAsModel(buffer, 0)
opcode_name = tflite.opcode2name(opcode_value)- Whether the package remains compatible with current TensorFlow versions despite abandonment.
- Whether the schema definitions in version 2.18.0 cover all operators in recent TFLite models.
- Security implications of using an abandoned package in production environments.
What it is and what it does
The tflite package provides a Python interface to read and inspect TensorFlow Lite model files. It wraps the FlatBuffers schema definitions that TFLite uses internally, allowing you to programmatically examine model structure, operators, tensors, and other metadata. The package includes convenience helpers like opcode-to-name mapping and compatibility fixes for API changes across versions.
You install it alongside a matching TensorFlow version, then import tflite and use its classes to load and traverse a .tflite model file. It depends on flatbuffers and numpy for deserialization and numerical operations. The package is intended for developers who need to analyze or validate TFLite models programmatically rather than run inference on them.
Use it for
- Inspect the operator graph and layer structure of a compiled TFLite model for debugging.
- Validate that a TFLite model contains expected operators before deployment.
- Extract metadata and tensor information from .tflite files for analysis pipelines.
- Programmatically check operator compatibility when managing model versioning.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
No.
The repository is archived and abandoned with no active maintenance. While install friction is low and licensing is permissive, relying on it carries risk: schema definitions may become out of sync with current TFLite versions, and no one will fix compatibility issues. Use only if locked to an older TensorFlow version and need to inspect legacy models.
Install
tflite on PyPI
Before you install
Low install friction with only two runtime dependencies (flatbuffers and numpy). However, the repository is archived and marked abandoned, with no active maintenance since the latest release.
Requires a matching TensorFlow version to be installed separately; schema definitions may not align with newer TFLite converter versions.
License in practice
Licensed under Apache License 2.0 (permissive). No licensing restrictions on use or redistribution.
Quickstart
pip install tflite==2.18.0
import tflite
model = tflite.Model.GetRootAsModel(buffer, 0)
opcode_name = tflite.opcode2name(opcode_value)Verify before relying
- Whether the package remains compatible with current TensorFlow versions despite abandonment.
- Whether the schema definitions in version 2.18.0 cover all operators in recent TFLite models.
- Security implications of using an abandoned package in production environments.
Package facts
| License | Apache License 2.0 permissive |
| Python support | Supports the current Python release !=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,<4,>=2.7 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesflatbuffersnumpy |
| Maintenance | Abandoned 563 days since the last release |
| Last repo commit | repository archived |
| First released | |
| Downloads | 123,332 / month, #11,912 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaEnvironment :: ConsoleIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseNatural Language :: EnglishOperating System :: OS IndependentProgramming Language :: Python :: 2Programming Language :: Python :: 2.7Programming Language :: Python :: 3Programming Language :: Python :: 3.5Programming Language :: Python :: 3.6Programming Language :: Python :: 3.7Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: tflite-2.18.0-py2.py3-none-any.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 › “tflite model parser”
- tfliteParses TensorFlow Lite (*.tflite) model files and provides a Python…
- litert-torchConverts PyTorch models to .tflite format for on-device deployment on…
- tf2onnxConverts TensorFlow, Keras, TensorFlow.js, and TFLite models to ONNX…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also tflite-runtime · litert-converter · onnx2tf · tf2onnx · litert-torch · tensorflow-datasets · tfds-nightly · ai-edge-model-explorer · tf-estimator-nightly · tensorflow-estimator