Metadata-Version: 2.4
Name: tinyq4
Version: 0.1.0
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Rust
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Summary: Minimal GGUF transformer runtime and OpenAI-compatible local chat server.
Keywords: gguf,llm,inference,rust,server
Home-Page: https://www.staticplay.co.uk/
Requires-Python: >=3.8
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
Project-URL: Homepage, https://www.staticplay.co.uk/

# tinyq4

`tinyq4` is a minimal Rust GGUF transformer runtime with an OpenAI-compatible
local chat completions server.

## Install

```bash
pip install tinyq4
```

## Run

Pass a GGUF model path explicitly:

```bash
tinyq4 /path/to/model.gguf --server 18081
```

Then check the server:

```bash
curl http://127.0.0.1:18081/health
```

The server exposes:

- `GET /health`
- `GET /v1/models`
- `POST /v1/chat/completions`

## Development

Build from source with Cargo:

```bash
cargo build --release
```

