LiteRT-LM

license

Apache-2.0(OSI)

source

public(the published repository is the engine)

core features withheld

no — no enterprise path in the repository root and no paid build of the engine in the README

LiteRT-LM's LICENSE is the stock Apache-2.0 text with no added restriction, and the public repository is the engine itself rather than a wrapper around closed code. Its root carries no enterprise or commercial directory, and the README describes no license-gated build, so nothing in the published source is held back.

• https://api.github.com/repos/google-ai-edge/LiteRT-LM recorded 2026-08-31

  Repo metadata for google-ai-edge/LiteRT-LM - archived false, 6,334 stars.

• https://raw.githubusercontent.com/google-ai-edge/LiteRT-LM/main/LICENSE recorded 2026-10-07

  LICENSE body, read in full: the stock Apache-2.0 text with no appended condition.

• https://raw.githubusercontent.com/google-ai-edge/LiteRT-LM/main/README.md recorded 2026-10-07

  README, read for a paid tier, an enterprise edition or a licence-gated build beside the published source, and for whether any component is stated to be private.

PyPI downloads of the litert-lm package are the adoption signal for this runtime. The package resolves to this repository, so the figure is the product's own rather than borrowed from a dependency.

• https://pypistats.org/api/packages/litert-lm/recent recorded 2026-08-31

  trailing 30-day download figure

LiteRT-LM sits two tiers below vLLM. It runs models on edge hardware rather than serving them from a datacenter, so it carries none of the batching, parallelism or multi-tenant serving that the higher-rated engines are built around.

• https://raw.githubusercontent.com/google-ai-edge/LiteRT-LM/main/README.md recorded 2026-10-07

  README "Key Features": Android, iOS, Web, Desktop and IoT support, GPU and NPU acceleration, vision and audio input and function calling; a litert-lm CLI, with Python, Kotlin and C++ listed as stable language APIs.