DeepSeek R1 is a state-of-the-art AI reasoning model that has garnered significant attention for its advanced capabilities and open-source accessibility. This guide provides an overview of its architecture, training methodology, hardware requirements, and instructions for local deployment on both Linux and Windows systems.

---

1. Architecture and Training

DeepSeek R1 was developed to enhance reasoning and problem-solving tasks. The model’s architecture and training methodologies have been detailed in various resources, highlighting its design and the processes involved in its development.

Read more on Medium

---

2. Hardware Requirements

Deploying DeepSeek R1 locally necessitates specific hardware configurations, especially concerning GPU capabilities. The requirements vary based on the model variant and quantization techniques employed.

Model Variant	Parameters (B)	VRAM Requirement (GB)	Recommended GPU Configuration
DeepSeek R1	671	~1,342	Multi-GPU setup (e.g., NVIDIA A100 80GB x16)
DeepSeek R1-Distill-Qwen-1.5B	1.5	~0.7	NVIDIA RTX 3060 12GB or higher
DeepSeek R1-Distill-Qwen-7B	7	~3.3	NVIDIA RTX 3070 8GB or higher
DeepSeek R1-Distill-Llama-8B	8	~3.7	NVIDIA RTX 3070 8GB or higher
DeepSeek R1-Distill-Qwen-14B	14	~6.5	NVIDIA RTX 3080 10GB or higher
DeepSeek R1-Distill-Qwen-32B	32	~14.9	NVIDIA RTX 4090 24GB
DeepSeek R1-Distill-Llama-70B	70	~32.7	NVIDIA RTX 4090 24GB (x2)

Note: The full DeepSeek R1 model requires substantial VRAM, making multi-GPU setups essential. Distilled versions are optimized for single-GPU configurations with lower VRAM.

---

3. Deploying DeepSeek R1 Locally with Ollama, Docker, and WebUI

Deploying DeepSeek R1 locally with a user-friendly web interface involves using Ollama, Docker, and Open WebUI. This guide provides detailed steps for installation and setup on both Linux and Windows systems.

Prerequisites

Hardware Requirements:

• RAM: Minimum 16GB recommended.
• Storage: At least 20GB of free space, preferably on an SSD for faster performance.
• GPU: A dedicated GPU (e.g., NVIDIA RTX 3060 or higher) is recommended for optimal performance but not mandatory.

Software Requirements:

• Operating System: Linux or Windows 10/11.
• Docker: Ensure Docker is installed and running.
• Ollama: A tool for managing and running AI models locally.

---

Installing Ollama

Linux:

1. Open a terminal.
2. Run the following command to install Ollama:

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

3. Verify the installation:

   ollama -v

Windows:

1. Download the Ollama installer from the official website.
2. Run the installer and follow the on-screen instructions.
3. After installation, open PowerShell and verify:

   ollama -v

---

Downloading DeepSeek R1 Model

Ollama allows you to download different variants of the DeepSeek R1 model based on your hardware capabilities.

• 1.5B Parameters (Approx. 1.1GB):

  ollama run deepseek-r1:1.5b

• 7B Parameters (Approx. 4.7GB):

  ollama run deepseek-r1

• 70B Parameters (Requires 24GB+ VRAM):

  ollama run deepseek-r1:70b

• Full 671B Model (Requires 300GB+ VRAM):

  ollama run deepseek-r1:671b

Note: For most users, the 1.5B or 7B models are recommended due to lower hardware requirements.

---

Setting Up Open WebUI with Docker

Open WebUI provides a graphical interface to interact with DeepSeek R1.

Install Docker:

• Linux: Follow the official Docker installation guide.
• Windows: Download and install Docker Desktop from the Docker website.

Run Open WebUI Container:

1. Open a terminal or PowerShell and execute:

   docker run -d -p 3000:8080 \
      --add-host=host.docker.internal:host-gateway \
      -v open-webui:/app/backend/data \
      --name open-webui \
      --restart always \
      ghcr.io/open-webui/open-webui:main

2. Access Open WebUI:

• Navigate to http://localhost:3000 in your web browser.
• On first access, you’ll be prompted to create an admin account.
• After logging in, select the appropriate DeepSeek R1 model (e.g., deepseek-r1:1.5b) to start interacting.

---

Troubleshooting Tips

• Model Loading Issues: If the model fails to load, ensure your system meets the hardware requirements and that there’s sufficient disk space.
• Docker Networking: If you encounter network-related errors, ensure Docker is configured correctly and that the necessary ports are open.
• Performance Optimization: For better performance, consider using a system with a dedicated GPU and ensure that your drivers are up-to-date.

---

Conclusion

By following these steps, you can successfully deploy DeepSeek R1 locally with a user-friendly web interface, leveraging Ollama, Docker, and Open WebUI. This setup ensures a seamless and efficient environment for interacting with the DeepSeek R1 model.