> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent-mintlify-f21cea86.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Local model quantization

> Create smaller GGUF models with a safe preview-first workflow.

```bash theme={null}
arka quantize model-f16.gguf --output model-q4.gguf --type Q4_K_M
arka quantize model-f16.gguf --output model-q4.gguf --type Q4_K_M --run
```

The first command previews the `llama-quantize` command. Add `--run` to
execute it; Arka creates the output directory automatically. Install a
llama.cpp build exposing `llama-quantize` before running conversions.


## Related topics

- [Local model optimization and setup](/guides/local-models.md)
- [Integrations](/guides/integrations.md)
- [Security model and prompt-injection defenses](/concepts/security.md)
- [Arka — AI terminal agent documentation](/index.md)
- [MCP integration for Cursor and Claude](/guides/mcp.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.