Back to Gap Map Model components / Inference code

Uzu

Mirai Tech
open source / Overall score: 2.5

Uzu is a high-performance on-device inference engine for Apple platforms, running models locally on iOS and macOS against unified memory so that inference needs no network round trip and no per-token cost. It ships Python, TypeScript and Swift bindings in-repo.

Openness

5 medium confidence
5.0
license
MIT(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

Uzu's LICENSE is the stock MIT text with no appended condition, 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.

Adoption

2 low confidence
2.0

Uzu is distributed mainly as Rust and Swift builds, so GitHub stars are its adoption signal. A `uzu` package does exist on PyPI and resolves to this repository, but its downloads measure a minority channel next to that primary distribution, so no package artifact is declared.

Capability

3 medium confidence
3.0

Uzu sits two tiers below vLLM, level with llamafile, the other single-target local engine here. It serves one hardware family and does not carry the multi-node or parallelism surface the higher tiers are built around.

Verified 2026-09-27