AI Potluck
Model components / Inference code

LiteRT-LM

Google

LiteRT-LM is Google's orchestration layer for running language models with LiteRT on edge devices, engineered for cross-platform on-device execution rather than datacenter serving. It is distributed as a command-line tool and as prebuilt C API shared libraries.

Verified 2026-08-31 via GitHub, the LICENSE body and the repository README.

Openness

5 medium confidence
5.0
license
Apache-2.0(OSI)
source
public(the published repository is the engine)
core-gated
ungated(no enterprise path in the repository root and no paid build of the engine in the README)

The LICENSE body is the stock Apache-2.0 text with no appended condition, read in full rather than taken from the API's label. The repository is public and unarchived and builds the engine itself. Its root tree carries no enterprise, ee or commercial directory and its README describes no licence-gated build, so the core reads as ungated. Confidence is medium because that is a repository-and-README read rather than a pricing-page read.

Adoption

2 medium confidence
2.0

22,328 downloads of litert-lm in the trailing 30 days, which bands at 10K-100K, level 2 on the software adoption scale. The package resolves to this repository, so the figure is the product's own.

Capability

3 medium confidence
3.0

Two bands below the vllm anchor. It runs models on edge hardware rather than serving them from a datacenter, so none of the batching, parallelism or multi-tenant surface the top bands rest on applies.

Verified 2026-08-31