> For the complete documentation index, see [llms.txt](https://docs.heyamica.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.heyamica.com/connecting-llms-your-core-ai-chatbot-model/using-koboldcpp.md).

# Using KoboldCpp

You can find the full KoboldCpp documentation [here](https://github.com/LostRuins/koboldcpp/blob/concedo/README.md).

### Step 1 - Clone the repo

```bash
git clone https://github.com/LostRuins/koboldcpp
cd koboldcpp
```

### Step 2 - Download the model

For example, we will use OpenChat 3.5 model, which is what is used on the demo instance. There are many models to choose from.

Navigate to [TheBloke/openchat\_3.5-GGUF](https://huggingface.co/TheBloke/openchat_3.5-GGUF) and download one of the models, such as `openchat_3.5.Q5_K_M.gguf`. Place this file inside the `./models` directory.

### Step 3 - Build KoboldCpp

```bash
make
```

### Step 4 - Run the server

```bash
./koboldcpp.py ./models/openchat_3.5.Q5_K_M.gguf
```

### Step 5 - Enable the server in the client

First select `KoboldCpp` as the backend in the client:

```md
settings -> ChatBot -> ChatBot Backend -> KoboldCpp
```

Then configure `KoboldCpp`:

```md
settings -> ChatBot -> KoboldCpp
```

Inside of "Use KoboldCpp" ensure that "Use Extra" is enabled. This will allow you to use the extra features of KoboldCpp, such as streaming.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.heyamica.com/connecting-llms-your-core-ai-chatbot-model/using-koboldcpp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.