Deploy DeepSeek Locally in 5 Minutes with Ollama
This guide walks you through downloading and installing Ollama, configuring storage and network settings, selecting and pulling the appropriate DeepSeek model version, and using a graphical interface such as Chatbox AI to interact with the locally running large language model.
1. Install Ollama
Ollama is an open‑source framework for running large language models locally. Download the installer for your operating system from the official Ollama website, run it, and verify the installation by opening a terminal and executing ollama help, which should display the help information.
2. Optional configuration
To avoid using the default C‑drive for model files, set the environment variable OLLAMA_MODELS to a directory on another drive (e.g., D:). For LAN access, set OLLAMA_HOST=0.0.0.0 and ensure the firewall allows the default port 11434.
3. Choose and download a DeepSeek model
DeepSeek offers several model sizes:
Low‑resource: 1.5 B (CPU‑only) or 7 B (GPU recommended).
High‑performance: 14 B / 32 B (requires ≥16 GB VRAM) or 70 B (requires ≥24 GB VRAM).
To pull a model, run a command such as: ollama run deepseek-r1:7b After downloading, list the available models with ollama list.
4. Interact via a graphical UI
Tools like Chatbox AI or Cherry Studio provide a visual interface for chatting with the locally hosted model. Install the chosen UI from its official site, launch it, and configure it to connect to the Ollama server (default address http://localhost:11434).
After configuration, you can start a conversation with the DeepSeek model as shown in the screenshots below.
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
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.