litert-lm-builder
Python tools for building and inspecting LiteRT-LM file formats
Decision gist · record as of 2026-08-14
Yes, if you are building or deploying LLMs to edge devices and need to work with LiteRT-LM model formats. The package is actively maintained, has no known vulnerabilities, low install friction, and permissive licensing. However, verify that you need the builder/inspection tools specifically—if you only need to run inference, you may need the full LiteRT-LM runtime separately.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; intended as a build/inspection tool for LiteRT-LM models rather than a standalone inference engine.
- Low install friction; pure Python wheel with four lightweight dependencies (protobuf, flatbuffers, absl-py, tomli).
- Active maintenance with release 6 days old and 6199 repository stars.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and research contexts.
last release 2026-08-08 (6 days) · last repo commit 2026-08-14 · 6,199 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 117,761 downloads/mo, #12,150 on PyPI
Alternatives
Verify before relying
pip install litert-lm-builder
from litert_lm_builder import ...
# See https://ai.google.dev/edge/litert-lm/python for API details- Specific Python API surface and available classes/functions for model building and inspection
- Whether this package alone can run inference or if it requires separate LiteRT runtime installation
- Performance characteristics and supported quantization formats beyond what the description mentions
What it is and what it does
LiteRT-LM-builder is Google's Python toolset for constructing and analyzing LiteRT-LM model files—the format used to run large language models efficiently on edge devices like phones, tablets, IoT boards, and browsers. It sits within a larger ecosystem (LiteRT-LM) that handles cross-platform, hardware-accelerated inference of models like Gemma, Llama, and others. The package depends on protobuf, flatbuffers, absl-py, and tomli to serialize and manipulate model definitions.
This is a builder and inspection tool, not a runtime engine itself. Developers use it to prepare, validate, and configure LiteRT-LM model files before deploying them to target platforms. It supports Python 3.10+ and is actively maintained by Google's AI Edge team, with the latest release arriving within days of the fact sheet date.
Use it for
- Prepare and validate Gemma or Llama models for on-device deployment on Android, iOS, or embedded Linux systems
- Build quantized model files (int4, E2B, E4B) optimized for specific hardware like mobile GPUs or NPUs
- Inspect and debug LiteRT-LM file formats to verify model configuration before production rollout
- Integrate model building into CI/CD pipelines for edge AI applications across multiple platforms
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building or deploying LLMs to edge devices and need to work with LiteRT-LM model formats.
The package is actively maintained, has no known vulnerabilities, low install friction, and permissive licensing. However, verify that you need the builder/inspection tools specifically—if you only need to run inference, you may need the full LiteRT-LM runtime separately.
Install
litert-lm-builder on PyPI
Before you install
Low install friction; pure Python wheel with four lightweight dependencies (protobuf, flatbuffers, absl-py, tomli). Active maintenance with release 6 days old and 6199 repository stars.
Requires Python 3.10 or later; intended as a build/inspection tool for LiteRT-LM models rather than a standalone inference engine.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and research contexts.
Quickstart
pip install litert-lm-builder
from litert_lm_builder import ...
# See https://ai.google.dev/edge/litert-lm/python for API detailsVerify before relying
- Specific Python API surface and available classes/functions for model building and inspection
- Whether this package alone can run inference or if it requires separate LiteRT runtime installation
- Performance characteristics and supported quantization formats beyond what the description mentions
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesprotobufflatbuffersabsl-pytomli |
| Maintenance | Actively maintained 6 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 117,761 / month, #12,150 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: litert_lm_builder-0.16.0-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 › “edge llm inference”
- litert-lm-builderProvides Python tools for building, inspecting, and working with…
- vllm-cpuvllm-cpu provides CPU-optimized inference for large language models…
- onnxruntime-genaiRuns small and large language models and multi-modal models on-device…
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 ai-edge-litert · litert-torch · onnxruntime-genai · ai-edge-litert-nightly · litert-converter · ai-edge-quantizer · tosa-adapter-model-explorer · ipex-llm · tflite-runtime · executorch