shimmy

App Listed

Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe.

Downloads
352
Dependents
Not applicable
Stars
6,014
Forks
587
Contributors
1
Commits
225
Latest release
2.6.6 ·

About

From the project README ·

Shimmy Logo

Shimmy — Local Inference, OpenAI-Compatible

🔒 Local GPU inference — Rust/WGSL application 🚀

Shimmy 2.6.6

Shimmy is a local inference server and CLI; Airframe 0.4.5 is its engine. This is a coordinated dense-text correctness, dependency-security and documentation release, not a new architecture or performance release. See CHANGELOG.

Default dependency licensing: Shimmy → Airframe → libfse. Shimmy is Apache-2.0; Airframe and airframe-observe are MIT; ShimmyTok is MIT OR Apache-2.0. The libfse 0.1.4 additional Apache-2.0 grant permits commercial use, modification, redistribution and incorporation into products without separate commercial permission. The original crates.io archive and metadata remain unchanged. Preserve component and third-party notices; see stack licensing.

Install and run

Verified native 2.6.6 archives and checksum instructions are available separately from crates.io, including the Windows executable and complete licensing bundles.

Install the versioned crate with a Rust toolchain:

cargo install shimmy --version 2.6.6 --locked
shimmy --version
shimmy --ctx 512 --kv-quant f32 serve --model-path /path/to/model.gguf --bind 127.0.0.1:11435
Read the full README

Use a verified admitted fixture in place of the path. A working Rust toolchain and GPU driver are required. The fast profile does not provide inference. The separately verified native downloads, Homebrew and Scoop installers and versioned GHCR image are now available for 2.6.6. A crates.io upload does not create those channels automatically. Docker latest is unchanged; npm is not included. Verify the exact installed version.

See quickstart for model hashes, listing, requests and network access. Unavailable translations are not linked as current guides.

Correctness and support

The exact fixture matrix covers selected Qwen3-0.6B/Qwen3-1.7B and Llama 3.2 3B Q4_K_M cases, with independent FP32 full logits, maximum absolute 0.1/RMS 0.03 gates and matching measured greedy decisions. These are bounded model/context/mode results, not universal family support.

F32 KV and reference kernels define the validated path. Parsing metadata, tokenizers or quantization is not certification. Gemma2, MoE, MLA, recurrent, state-space and multimodal executors are not enabled. INT4/TurboShimmy and experimental kernels remain excluded and rejected.

Executed full-logit GPU evidence is NVIDIA through WSL Dozen/Vulkan. NOT_RUN for full-logit certification: Metal/M4, other unexecuted native GPU platforms, extended-context Llama, alternate prefill chunks and unlisted combinations. WSL device-destruction and active-generation device-loss investigations remain open. No universal determinism, startup, multi-GPU, memory or speed guarantee is made.

Server contract

Selected OpenAI-compatible endpoints provide model listing, JSON chat/text completions and explicit chat-only SSE. Chat defaults to JSON; text streaming rejects. Usage, stop/finish metadata and typed errors are part of the tested contract. This is not every OpenAI endpoint/SDK feature.

Loopback can run without a key. Non-loopback binds require SHIMMY_API_KEY; browser origins require SHIMMY_ALLOWED_ORIGINS. With a key, routes except GET /health require credentials; origin checks still apply to health. Use TLS and appropriate network access controls remotely. Lazy loading is the default; optional selected-model warm-up shifts cold work before readiness without eliminating it or guaranteeing stability.

Documentation

Shimmy source is Apache-2.0. Airframe runtime and Observe are MIT; ShimmyTok is dual-licensed. libfse 0.1.4 is covered by the additional Apache-2.0 grant, permitting commercial use without separate permission. Preserve applicable component, dependency and model terms; see stack licensing.

Support

This project is independently maintained. Component licensing terms described above apply. Sponsorship helps fund ongoing development, certification, compatibility work, and releases.

Sponsor on GitHub · Buy Me a Coffee

Any amount is appreciated. Suggested tiers:

  • $5/month — Thanks
  • $15/month — Supporter
  • $50/month — Backer
  • Custom — Email for invoicing

License & Philosophy

Shimmy server code: Apache-2.0 — see LICENSE. The default dependency stack permits commercial use under its component terms, including the libfse additional grant. See stack licensing; original published archives remain unchanged.

Promise: This will never become a paid product.

Shimmy is infrastructure: it should be invisible. Reliability through comprehensive validation and property-based testing.


Maintainer: Michael A. Kuykendall · Mission: Making local model inference simple and reliable


Support

This project is a safe space. Trans rights are human rights.

If you or someone you love needs support:

Runs on
GPU support unknown
What shows it
  • no dependency or feature matches a backend row
Native code
Required
  • Binds native code: sys-info
Python bindings
No Python binding crate found
License
Apache-2.0

Compare with similar projects

Order: strongest tier first, then most downloads, then name, with unmeasured values last. A library counts downloads over 30 days. An app counts binary downloads per release. An app with none counts its crate downloads over 30 days. ML Rust runs this catalogue, so its closest project always gets a row.

shimmy beside the projects that share a topic with it
ProjectDownloadsDependentsStarsLatest releaseRuns on (GPU)Native codeLicense
shimmy This page App Listed

Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe.

352 binary downloads per release Not applicable 6,014 2.6.6 GPU support unknown Binds native code: sys-info Apache-2.0
orp Listed

Lightweight framework for building ONNX runtime pipelines with ort

Also in Run and serve models.

41,463 downloads over 30 days 6 14 1.0.0 CUDA, ROCm Binds native code: ort-sys Apache-2.0
oxionnx Listed

Pure Rust ONNX inference engine — zero C/C++ dependencies

Also in Run and serve models.

550 downloads over 30 days 24 20 0.1.7 CUDA, WebGPU No native code found Apache-2.0
candle-vllm App Listed

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

Also in Build LLM apps and agents.

138 binary downloads per release Not applicable 739 Not measured Not measured MIT
blazr App Listed

Inference server for LLMs, speech and embeddings: OpenAI-compatible routes with streaming, plus speech synthesis (TTS) and transcription (ASR). Serves Llama, Mistral, Qwen, Mamba2, MLA+MoE and hybrid models from SafeTensors, AWQ, GPTQ and GGUF.

Also in Build LLM apps and agents.

8 binary downloads per release Not applicable 7 0.7.1 CUDA, WebGPU Binds native code: ring (feature distributed) Apache-2.0

Fast, unified, Rust-native, Axum-compatible inference endpoints and nervous system for tensor models and LLMs: KServe / Triton and OpenAI APIs from one pure-Rust server

Also in Build LLM apps and agents.

241 downloads over 30 days 0 66 0.16.2 CUDA, WebGPU, Metal No native code found MIT
Why ListedNo archive, New or Featured rule places it, so it is Listed.

What it lacks for Featured

  • The check holds no value for Homebrew installs on request over 365 days, Repology repository families, Docker pull growth over 90 days. A gate that lacks its signal does not pass.

What else the check found

  • The last activity is on 7 Nov 2026, 2 days ago. The rules expect an update within 365 days. Dormancy rule

Not measured: Homebrew installs on request over 365 days, Repology repository families, Docker pull growth over 90 days.

Exact rules: Listed, Featured app. The check on applied thresholds version 9.

Every rule outcome, as the check records it
  • expected-interval: app: E = 365 days
  • dormancy: last activity 2026-11-07, 2 days ago, E = 365: active
  • featured: not featured: unknown homebrew_on_request_365d, repology_families, docker_pull_growth_90d
  • listed: listed: no archive, new or featured rule applies

Measurements and sources

Each signal row shows the raw value, its source and the fetch date. The Sources list gathers every distinct source on this page. Movement needs more history.

Sources6 sources
Adoption352 binary downloads per release4 not measured
Adoption measurements
SignalValueSourceFetchedCounts
Active dependentsNot measuredYes
New dependents (365 days)Not measuredYes
Peak active dependentsNot measuredYes
Active dependents as a share of the peakNot measuredYes
Binary downloads per release352GitHub releasesYes
MaintenanceLatest human commit: 2 days ago4 not measured
Maintenance measurements
SignalValueSourceFetchedCounts
Latest human commit2026-11-07GitHub repositoryYes
Latest release2026-11-07GitHub releasesYes
First release2025-09-04crates.io database dumpYes
Latest version2.6.6crates.io database dumpNo
Days the oldest outside issue waits for a reply46GitHub repositoryYes
Maintainer replies over 365 days82GitHub repositoryYes
Repository archivedfalseGitHub repositoryYes
Repository gonefalseGitHub repositoryYes
Release commit or manifest in the repotruecrates.io packageNo
Published docsNot measuredYes
Latest release fails cargo checkNot measuredYes
Build check dateNot measuredYes
Build check toolchainNot measuredYes
SecurityNot measured
Security measurements
SignalValueSourceFetchedCounts
Unpatched vulnerabilities past the grace windowNot measuredYes
RustSec unmaintained advisoryNot measuredYes
Deprecation noticeNot measuredYes
Deprecated requirementNot measuredYes
Distribution34 releases, 259 downloads over 30 days6 not measured
Distribution measurements
SignalValueSourceFetchedCounts
Releases34crates.io database dumpNo
Downloads over 30 days259crates.io database dumpNo
Binary downloads over the last 3 releases1057GitHub releasesYes
Homebrew installs on request over 365 daysNot measuredYes
Repology repository familiesNot measuredYes
Docker pull growth over 90 daysNot measuredYes
Docker pulls at the growth baselineNot measuredYes
Every version a prereleasefalsecrates.io database dumpYes
Every version 0.0.xfalsecrates.io database dumpYes
Every version yankedNot measuredYes
Crate deleted from crates.ioNot measuredYes
Repository6,014 stars, 587 forks, 1 contributors, 225 commits. Stars alone never qualify a project.
Repository measurements
SignalValueSourceFetchedCounts
GitHub stars6014GitHub repositoryYes — one part of the repository route
GitHub forks587GitHub repositoryYes — one part of the repository route
Contributors with a GitHub account1GitHub contributorsYes — one part of the repository route
Commits on the default branch225GitHub repositoryNo
Repository's main crate left out of the entrynonecrates.io database dumpYes
Facts that never count
Facts that never count measurements
SignalValueSourceFetchedCounts
LicenseApache-2.0crates.io database dumpNo
Runs on, from listed crates and their direct dependenciesGPU support unknowncrates.io database dumpNo
What shows each backendno dependency or feature matches a backend rowcrates.io database dumpNo
Native code, from listed crates and their dependenciesBinds native code: sys-infocrates.io database dumpNo
Python bindings, from direct dependencies of listed cratesNo Python binding crate foundcrates.io database dumpNo
Crates that depend on a listed crate directlyNot measuredNo

Corrections and review history

Report a correction

No correction applies to this entry.

Judgments

A judgment enters only through an approved issue and a merged pull request.

No judgment applies to this entry.