Deploying the DeepSeek Large Language Model Locally with Ollama on Windows
This guide explains how to install Ollama on a Windows machine, configure its environment, and use it to download and run the DeepSeek‑R1 1.5B large language model locally, enabling offline AI interactions without relying on remote servers.
In the current AI era, developers who are unfamiliar with AI technologies risk falling behind, and the popular DeepSeek large language model is worth learning about, especially when remote servers are often busy.
1. Download and Install Ollama
Ollama is an open‑source platform for running large language models locally, suitable for developers, researchers, and students. Download the Windows installer from the official website, then copy the installer (OllamaSetup.exe) to a dedicated folder on the D: drive.
Open a command prompt with administrator rights, switch to the D: drive, and set the model storage path:
setx OLLAMA_MODELS "D:\Ollama\models" /M
Install Ollama to the chosen directory:
OllamaSetup.exe /dir=D:\Ollama
After installation, verify the version with ollama -v and ensure the Ollama icon appears in the taskbar.
2. Download and Run the DeepSeek Model
Visit the Ollama website, click the DeepSeek‑R1 link, and select the smallest 1.5B variant. Copy the displayed command and execute it to download the model:
ollama pull deepseek-r1:1.5b
Once the download completes, replace pull with run to start the model and begin chatting:
ollama run deepseek-r1:1.5b
After the model is running locally, you can interact with DeepSeek directly from your machine.
The article concludes by inviting readers to follow the public account for future updates and to leave comments with any questions.
Full-Stack Internet Architecture
Introducing full-stack Internet architecture technologies centered on Java
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.