Shimmy

Pure-Rust WebGPU inference engine, OpenAI-API compatible, running on any GPU.

Servicefreeglobal

Shimmy is a self-hosted, pure-Rust WebGPU inference engine that is OpenAI-API compatible and GGUF native, running on any GPU as a single binary with no Python or llama.cpp dependency. It's built for developers who want a lightweight, dependency-free local LLM inference server instead of setting up a Python-based inference stack.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Shimmy - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Shimmy to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Shimmy (or something else) actually fits.

Try a problem