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

> ## Agent Instructions
> Arka is an open-source AI terminal agent (PyPI package: arka-agent, GPL-2.0).
> Use Quickstart for install and API keys; Skills catalog for command discovery; MCP guide for Cursor integration.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# In-engine speculative decoding

> Configure draft models for faster local generation.

```bash theme={null}
arka speculative vllm --draft-model qwen3:1.7b
arka speculative vllm --draft-model qwen3:1.7b --num-draft-tokens 6 --apply
```

Arka stores draft settings without claiming that every runtime supports them.
The active vLLM, Exo, Ollama, or MLX build must expose speculative-decoding
options when launched. Verify generated output quality and latency after
enabling it.


## Related topics

- [Easy AI model hosting setup](/guides/model-hosting.md)
- [Voice control with wake word, STT, and TTS](/guides/voice.md)
- [Engineering loops](/guides/loop-engineering.md)
- [Reverse-engineer a repository](/guides/repo-reverse.md)
- [Running the autonomous goal agent](/guides/goal-agent.md)