Running DeepSeek-R1 and Qwen2.5 Locally with Ollama

Introduction

With the increasing popularity of open-source AI models, running powerful LLMs like DeepSeek-R1 and Qwen2.5 locally has become more accessible than ever. These models offer cutting-edge capabilities for natural language processing (DeepSeek-R1) and multimodal AI (, allowing users to leverage them for diverse applications like chatbots, summarization, code generation, and image-based reasoning.

To read more about DeepSeek, check out my other article on it — here

Ollama is a lightweight and easy-to-use tool designed to run LLMs on local machines efficiently. It simplifies downloading, managing, and running models without the need for complex dependencies or cloud-based APIs.

What is Ollama?

Source — https://ollama.com/

Ollama is an open-source framework that enables users to run LLMs locally with minimal setup. It provides a seamless interface to download and execute various models, making it an excellent choice for developers, researchers, and AI enthusiasts who want to experiment with AI capabilities offline. Key features include:

• Simple installation and model management
• Support for a variety of open-source models
• Local execution with optimized performance
• Interactive chat and inference capabilities

Uses of Ollama

Ollama enables a variety of AI-powered applications, including:

• Local AI Chatbots — Run interactive chat models without needing internet access.
• Text Summarization — Process large text inputs and generate concise summaries.
• Code Generation — Use models like DeepSeek-R1 to generate or complete code.
• Multimodal Processing — Utilize Qwen2.5-VL for image-based reasoning and vision-language tasks.
• AI-Assisted Writing — Enhance content creation with AI-powered assistance.

How to Install Ollama

Installation on macOS/Linux

Open a terminal and run:

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

Installation on Windows

Windows users need WSL 2 (Windows Subsystem for Linux). Once WSL is installed, follow the macOS/Linux installation command in the WSL terminal.

After installation, verify that Ollama is working by running:

ollama --version

How to Run Ollama

Once installed, start the Ollama service by running:

ollama serve

This will allow you to interact with models locally.

How to Pull Any Model

To download and use a model, use the following command:

ollama pull <model-name>

For example, to pull DeepSeek-R1:

ollama pull deepseek-r1

To pull Qwen2.5:

ollama pull qwen2.5

How to Chat with the Models

Once a model is pulled, you can start a chat session:

ollama run deepseek-r1

Source — Deepseek.com

For a multimodal model like Qwen2.5, you can input both text and images:

ollama run qwen2.5

To exit the chat, use Ctrl+C.

Useful Ollama Commands

Here are some handy commands to interact with Ollama:

• List available models:

ollama list

• Show details of a model:

ollama show deepseek-r1

• Remove a model:

ollama rm deepseek-r1

• Run a model with a custom prompt:

ollama run deepseek-r1 "Summarize this article for me."

References and Citations

1. DeepSeek-R1 Paper & GitHub: https://github.com/deepseek-ai
2. Qwen2.5 Model: https://huggingface.co/Qwen
3. Ollama Documentation: https://ollama.com

By following this guide, you can easily run state-of-the-art AI models locally without requiring cloud-based resources, ensuring efficiency and privacy while exploring AI capabilities.

Stay on the cutting-edge of AI! 🌟 Follow me on Medium, connect on LinkedIn, and explore latest trends in AI technologies and models. Dive into the world of AI with me and discover new horizons! 📚💻