Michael-A-Kuykendall / shimmy
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Why this job: says: llama.cpp, inference engine, gguf; topics: llamacpp, llm-inference, gguf, local-ai, llama
What it does
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.
Get started
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 - Maintenance
- Active
- Last commit 3 days ago
- Stars
- 6,015
- +9 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v2.6.6
- Released 3 days ago
- Built with
- Rust
- 83% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 94% closed
- 9 still open
- Pull requests
- 28 merged
- 0 waiting
- Releases
- 43
- 18 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| jundot / omlx | 23,491 | 5 days ago | Apache-2.0 | Mac |
| awaescher / OllamaSharp | 1,413 | 5 days ago | MIT | No downloads |
| llamastash / llamastash | 293 | yesterday | MIT | Mac, Windows, Linux |
More: download files, languages, topics and project record
Download files, v2.6.6
- Mac2 files, 38 downloads
- Windows2 files, 63 downloads
- Linux4 files, 76 downloads
Languages
- Rust 83%
- Shell 7%
- Python 4%
- TOML 2%
Topics
- llama
- llamacpp
- llm-inference
- ollama-api
- command-line-tool
- gguf
- inference-server
- local-ai
- machine-learning
- api-server
- developer-tools
- huggingface
Project record
- JobLocal LLMs
- StatusListed
- Commits225
- Forks587
- Watching41
- Stars in 28 days+51
- CreatedAug 28, 2025
- First seen by usNov 7, 2026
- CheckedNov 10, 2026