README.md

---
library_name: rkllm
license: mit
language:
- en
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
tags:
  - rkllm
  - rknn-llm
  - rk3588
  - rockchip
  - edge-ai
  - llm
  - deepseek
pipeline_tag: text-generation
---
# DeepSeek-R1-Distill-Llama-8B — RKLLM build for RK3588 boards

### Built with DeepSeek

**Author:** @jamescallander  
**Source model:** [deepseek-ai/DeepSeek-R1-Distill-Llama-8B · Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)  
**Target:** Rockchip RK3588 NPU via **RKNN-LLM Runtime**

> This repository hosts a **conversion** of `DeepSeek-R1-Distill-Llama-8B` for use on Rockchip RK3588 single-board computers (Orange Pi 5 plus, Radxa Rock 5b+, Banana Pi M7, etc.). Conversion was performed using the [RKNN-LLM toolkit](https://github.com/airockchip/rknn-llm?utm_source=chatgpt.com)

#### Conversion details

- RKLLM-Toolkit version: v1.2.1
- NPU driver: v0.9.8
- Python: 3.12
- Quantization: `w8a8_g128`
- Output: single-file `.rkllm` artifact
- Tokenizer: not required at runtime (UI handles prompt I/O)

## Intended use

- On-device inference on RK3588 SBCs.
- **Reasoning-focused** model — designed to handle multi-step thinking, problem-solving, and structured explanations.
- Well-suited for tasks that need **step-by-step reasoning** or more careful breakdowns than typical instruction models.

## Limitations

- Requires 9GB free memory
- Quantized build (`w8a8_g128`) may show small quality differences vs. full-precision upstream.
- Tested on Radxa Rock 5B+; other devices may require different drivers/toolkit versions.
- While strong at reasoning, performance is limited by RK3588’s NPU compared to high-end GPUs.

## Quick start (RK3588)

### 1) Install runtime

The RKNN-LLM toolkit and instructions can be found on the specific development board's manufacturer website or from [airockchip's github page](https://github.com/airockchip).

Download and install the required packages as per the toolkit's instructions.

### 2) Simple Flask server deployment

The simplest way the deploy the `.rkllm` converted model is using an example script provided in the toolkit in this directory: `rknn-llm/examples/rkllm_server_demo`

```bash
python3 <TOOLKIT_PATH>/rknn-llm/examples/rkllm_server_demo/flask_server.py \
  --rkllm_model_path <MODEL_PATH>/DeepSeek-R1-Distill-Llama-8B_w8a8_g128_rk3588.rkllm \
  --target_platform rk3588
```

### 3) Sending a request

A basic format for message request is:

```json
{
    "model":"DeepSeek-R1-Distill-Llama-8B",
    "messages":[{
        "role":"user",
        "content":"<YOUR_PROMPT_HERE>"}],
    "stream":false
}
```

Example request using `curl`:

```bash
curl -s -X POST <SERVER_IP_ADDRESS>:8080/rkllm_chat \
    -H 'Content-Type: application/json' \
    -d '{"model":"DeepSeek-R1-Distill-Llama-8B","messages":[{"role":"user","content":"In 2 or 3 sentences, who was Napoleon Bonaparte?"}],"stream":false}'
```

The response is formated in the following way:

```json
{
    "choices":[{
        "finish_reason":"stop",
        "index":0,
        "logprobs":null,
        "message":{
            "content":"<MODEL_REPLY_HERE">,
            "role":"assistant"}}],
        "created":null,
        "id":"rkllm_chat",
        "object":"rkllm_chat",
        "usage":{
            "completion_tokens":null,
            "prompt_tokens":null,
            "total_tokens":null}
}
```

Example response:

```json
{"choices":[{"finish_reason":"stop","index":0,"logprobs":null,"message":{"content":"","role":"assistant"}}],"created":null,"id":"rkllm_chat","object":"rkllm_chat","usage":{"completion_tokens":null,"prompt_tokens":null,"total_tokens":null}} 
```

#### Note on reasoning traces

This model outputs **intermediate reasoning text** (e.g., chains of thought) before its final response, enclosed by `</think>` markers.

- Many OpenAI-compatible UIs automatically **suppress or hide this internal reasoning**.
- If your client does not, you may see the reasoning steps along with the final answer.

### 4) UI compatibility

This server exposes an **OpenAI-compatible Chat Completions API**.

You can connect it to any OpenAI-compatible client or UI (for example: [Open WebUI](https://github.com/open-webui/open-webui?utm_source=chatgpt.com))

- Configure your client with the API base: `http://<SERVER_IP_ADDRESS>:8080` and use the endpoint: `/rkllm_chat`
- Make sure the `model` field matches the converted model’s name, for example:

```json
{
 "model": "DeepSeek-R1-Distill-Llama-8B",
 "messages": [{"role":"user","content":"Hello!"}],
 "stream": false
}
```

# License

This conversion follows the [MIT License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md)

- Attribution: **Built with DeepSeek-R1-Distill-Llama-8B (DeepSeek-AI)**
- Required notice: see [`NOTICE`](NOTICE)
- Modifications: quantization (w8a8_g128), export to `.rkllm` format for RK3588 SBCs