Build a Local DeepSeek‑R1 Large Model Service with Ollama – Intro to AI LLMs
This guide walks through installing Ollama on Windows, configuring the OLLAMA_MODELS path, downloading the 7‑b DeepSeek‑R1 model, running it locally, and accessing it via a browser using the Page Assist extension, providing step‑by‑step commands, screenshots, and tips for offline setups.
Overview
Ollama is a local large‑model manager that installs, runs and manages LLMs on Windows, macOS and Linux. It provides a local HTTP API (port 11434) for application integration.
1. Install Ollama
Download the installer from https://ollama.com/ (Windows 11 version shown). Run OllamaSetup.exe and follow the wizard. After installation, open a command prompt and execute ollama; the UI appears, confirming a successful start.
2. Configure model storage
By default models are stored in C:\Users\<username>\.ollama\models. To place models on another drive, set the environment variable OLLAMA_MODELS to the desired folder and restart Ollama.
3. Download a model
Search for deepseek-r1 on the Ollama website. The model has 7 B parameters (~4.7 GB). Run: ollama run deepseek-r1 The command pulls the model files into the blobs directory and creates a manifest directory with metadata.
4. Run and test the model
After the download completes, the model runs automatically. In the prompt, type a simple query such as “1+1?”. The response includes a think tag that shows the model’s reasoning steps.
5. Common Ollama commands
ollama -h # show help
ollama list # list installed models
ollama restart # restart the service
ollama update # update Ollama
ollama serve # run as a background service
ollama pull <model> # download without running
ollama run <model> # run (downloads if missing)
ollama rm <model> # delete a local model6. Access the model via a web UI
Ollama listens on http://127.0.0.1:11434. Install the Chrome extension “Page Assist” (or an equivalent client) and set the Ollama URL to the same address. The extension detects the running model, lets you select it, and provides a chat‑style interface for interaction.
7. Offline deployment
On a machine with internet access, install Ollama and pull the required model. Copy the entire Ollama installation folder and the directory referenced by OLLAMA_MODELS to the offline machine. Install Ollama there, set OLLAMA_MODELS to the copied folder, and run the model without network connectivity.
Fun with Large Models
Master's graduate from Beijing Institute of Technology, published four top‑journal papers, previously worked as a developer at ByteDance and Alibaba. Currently researching large models at a major state‑owned enterprise. Committed to sharing concise, practical AI large‑model development experience, believing that AI large models will become as essential as PCs in the future. Let's start experimenting now!
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.