DeepSeek-R1 로컬 컴퓨터에 설치

 

 

테스트 하는  PC 사양은 아래와 같습니다.

 

AMD 7950x

RAM : 64G

SSD : nvme 1TB

GPU : RTX 3060

 

# 우분투 리눅스에 설치

sudo apt update && sudo apt upgrade
sudo apt install curl  // 설치되어 있다면 건너뜀

sudo apt install apt-transport-https ca-certificates curl software-properties-common -y
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt update
sudo apt install docker-ce docker-ce-cli containerd.io

sudo systemctl start docker
sudo systemctl enable docker

sudo curl -L "https://github.com/docker/compose/releases/download/v2.29.3/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
docker-compose --version

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

 

아래와 같이 설치가 완료됨

root@Server:/home/kimchi# curl -fsSL https://ollama.com/install.sh | sh
>>> Installing ollama to /usr/local
>>> Downloading Linux amd64 bundle
######################################################################## 100.0%
>>> Creating ollama user...
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
>>> Downloading Linux ROCm amd64 bundle
######################################################################## 100.0%
>>> The Ollama API is now available at 127.0.0.1:11434.
>>> Install complete. Run "ollama" from the command line.
>>> AMD GPU ready.
root@Server:/home/kimchi#

 

요즘 바이브 코딩이 유행이라 딥시크 코드를 실행해 본다.

 

 

root@Server:/home/kimchi# ollama run deepseek-coder:33b

 

아래처럼 나오면 성공

pulling manifest
pulling 065b9a7416ba... 100% ▕███████████████████████████████████████████████████████████████████████████████████▏  18 GB
pulling a3a0e9449cb6... 100% ▕███████████████████████████████████████████████████████████████████████████████████▏  13 KB
pulling 8893e08fa9f9... 100% ▕███████████████████████████████████████████████████████████████████████████████████▏   59 B
pulling 8972a96b8ff1... 100% ▕███████████████████████████████████████████████████████████████████████████████████▏  297 B
pulling 1fe1cf68a363... 100% ▕███████████████████████████████████████████████████████████████████████████████████▏  484 B
verifying sha256 digest
writing manifest
success
>>> hello
Hello! How can I assist you with your programming or computer science queries today?


>>>

 

 

위 방법도 있지만 우리는 Chat GPT 처럼 웹 방식이 더 익숙하기에... 

 

 

git clone https://github.com/ollama-webui/ollama-webui.git

cd ollama-webui 

docker-compose up -d --build

 

 

웹브라우저로 접속해본다.

 

http://192.168.1.204:3000

 

웹 UI

 

웹으로 접속해서 관리자 계정을 등록하고 설정메뉴에서 모델을 추가한다.

 

Chat GPT 같은 UI