> ## Documentation Index
> Fetch the complete documentation index at: https://koharu.rs/llms.txt
> Use this file to discover all available pages before exploring further.

# Configure translation

> Set language, project instructions, quantization, sampling, and image input.

Choose output settings in the processing selector or **Settings → Translation**. Koharu captures them when a run starts; edits affect later runs.

## Language and instructions

Set the target language and concise project-wide guidance for names, terminology, tone, pronouns, formatting, or text that should remain untranslated. Test the instructions on several pages and correct OCR first.

## Local quantization

GGUF models may offer multiple quantizations. Smaller files need less download space and memory, usually at a quality cost. Larger files can be slower or exceed available memory. Hosted providers control their own serving precision.

## Generation controls

| Control                               | What to adjust                                           |
| ------------------------------------- | -------------------------------------------------------- |
| Temperature, top P, top K, min P      | Sampling and randomness                                  |
| Repeat, frequency, presence penalties | Repetition behavior                                      |
| Maximum output tokens                 | Response length budget                                   |
| Thinking mode                         | Additional reasoning for supported models                |
| Vision input                          | Whether a supported model receives the source page image |

<Tip>
  Start with provider defaults and change one variable at a time. High randomness tends to make
  names and terminology less consistent.
</Tip>

Thinking can increase latency and token use. Unsupported options may be ignored or rejected by a provider or model.

## Text and vision inputs

Text-only requests send semantic source text. With **Vision input**, a capable model also receives the source page image. For a custom OpenAI-compatible server, enable this only after checking image-message support.

Generated translations remain editable project data. [Review the wording and page layout](/en/guides/review) before export.