Search for DeepSeek-R1 and choose the version that fits your setup. The 1.5 billion or 7 billion parameter models are ideal for most setups.
Copy the boot command for your chosen model and paste it into the terminal or command line.
The model will begin downloading and once complete it will be ready for use.
Step 3: Run DeepSeek-R1 Locally
Now that DeepSeek-R1 is booted, you can start using it to solve complex logic problems.
How to Run DeepSeek-R1 Locally
Open a terminal or command prompt .
Enter a simple command, for example, ollama peru mobile database deepseek-r1 helloto test the model. You will see how the model starts its reasoning process step by step.
As the prompt is processed, the model will provide a more meaningful response than traditional LLMs , demonstrating its reasoning along the way.
DeepSeek-R1 Key Features and Specifications
Peculiarity Feature 2 Feature 3 Feature 4
Free to use Open source availability Works locally on your computer Flexible model sizes
Step by step reasoning Detailed explanations of the process Powerful for complex tasks Supports integration with N8N and Flowwise AI
Different sizes of models Parameters from 1.5B to 671B Ideal for programming, math and puzzles. Safe and confidential
2. Step-by-step guide to running DeepSeek-R1 locally deploying the model locally
Step 1: Set up your environment
The first step is to prepare the system to run DeepSeek-R1 . This includes installing the necessary software and dependencies.
1. Install Python and Pip : Make sure you have Python 3.8 or higher installed. You can download it from the official Python website.
2. Set up a virtual environment : Use venvor condato create an isolated environment for your project.