DeepSeek Deployment

This document demonstrates how to deploy DeepSeek locally on the Quectel Pi H1 single-board computer.

DeepSeek is a high-performance open-source large language model developed by a Chinese team. It features powerful natural language understanding, code generation, and logical reasoning capabilities. It can efficiently run in a local environment and is suitable for a variety of scenarios such as intelligent Q&A, text generation, and code assistance.

Prerequisites

1.The Quectel Pi H1 Debian system has been successfully flashed and booted.

2.The system can access the Internet normally.

Update Software Sources

Run the following command in the terminal:

sudo apt update
sudo apt upgrade

Before installing any software, it is recommended to update the system packages to ensure that all dependencies are up to date.

Install basic tools

sudo apt install curl

curl is a commonly used command-line download tool, which will be needed later when installing Ollama.

If the system indicates that curl is already installed, you can skip this step.

Install Ollama

Ollama is a lightweight model runtime environment that allows you to deploy and run various open-source AI models locally.

Run the following command in the terminal:

curl -fsSL https://ollama.com/install.sh | sh

Start the Ollama Service

Ollama needs to run a background server process to manage models.

Open a terminal and execute:

ollama serve

Keep this terminal window open

Run the DeepSeek Model

Open another terminal window and run the following command to pull and start the DeepSeek-R1 1.5B model:

ollama run deepseek-r1:1.5b

You can type text for conversation in the highlighted area, for example: