https://github.com/lasithaamarasinghe/deepseek-r1-local

Simple Guide to Run DeepSeek-R1 Locally with Ollama
https://github.com/lasithaamarasinghe/deepseek-r1-local

deepseek-r1

Last synced: 2 months ago
JSON representation

Simple Guide to Run DeepSeek-R1 Locally with Ollama

• Host: GitHub
• URL: https://github.com/lasithaamarasinghe/deepseek-r1-local
• Owner: LasithaAmarasinghe
• Created: 2025-02-04T11:31:34.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2025-02-05T02:21:32.000Z (3 months ago)
• Last Synced: 2025-02-05T03:22:43.386Z (3 months ago)
• Topics: deepseek-r1
• Homepage:
• Size: 5.86 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# How to Run DeepSeek-R1 Locally with Ollama

This guide explains how to set up and run **DeepSeek-R1** locally using **Ollama**. Follow the steps below to download the necessary software, choose the right model version, and run the DeepSeek-R1 model.

---

## Step 1: Download and Install Ollama

To start, you need to download and install **Ollama**, which allows you to run language models locally.

1. Go to the [Ollama Download Page](https://ollama.com/download).

2. Select the version that matches your operating system.

   ![Ollama download](https://github.com/user-attachments/assets/3a7c8a20-1e6f-4473-98f2-f0092f057768)

---

## Step 2: Choose the Model Version

After installing Ollama, you'll need to select the appropriate version of DeepSeek-R1.

1. Visit the [DeepSeek-R1 Library](https://ollama.com/library/deepseek-r1).

2. Select the model version that fits your system's capabilities

   - Available versions: **1.5b, 7b, 8b, 14b**, etc.

   - Choose a model based on your computer’s performance. Higher models require more memory and processing power.

   ![Model Selection](https://github.com/user-attachments/assets/88154691-f290-4766-9ef7-6a9c2f403e3f)

---

## Step 3: Run DeepSeek-R1 on Ollama

Once you have installed Ollama and selected your model, you can run **DeepSeek-R1** locally.

1. Open your terminal or command prompt.

2. Run the following command:  (replace n with the version you choose)

   ```bash

   ollama run deepseek-r1-nb

![image](https://github.com/user-attachments/assets/24bac0af-ffa5-4de7-979e-034d26378629)

## Step 4: Interact with the Model

Once DeepSeek-R1 is running, you can start interacting with it.

1. In your terminal, simply type your questions or commands.

2. The model will respond to your input accordingly.

![image](https://github.com/user-attachments/assets/f3c8bdda-0d1e-44b3-8f5c-64d983e51a43)