Running DeepSeek Locally: A Step-by-Step Guide

This is a quick walkthrough of how to run DeepSeek locally using LM Studio, which is free and doesn't require registration. In a few steps you can run a capable model on your own machine, privately and without usage limits.

Step 1: Download LM Studio

Head over to LM Studio's download page, select your operating system, and click the download button.

Step 2: Install LM Studio

After downloading, run the installer and follow the on-screen instructions. Once installed, launch LM Studio to begin exploring its features.

Step 3: Find a DeepSeek Model

Inside LM Studio, find the sidebar on the left and click the Discover tab (the purple icon). From there you can search for models that suit your hardware.

If you're not sure what your computer can handle, start with DeepSeek Qwen 7b. On a modern Mac or a powerful gaming PC, go for DeepSeek Qwen 14b instead.

Step 4: Download and Load Your Model

Once you've picked a model, click the download button at the bottom right of the window. The download can take a while, since the files range from 4.5GB to 9GB.

When it finishes, go to the Chat tab in the sidebar. At the top you'll see a prompt saying "select a model to load". Choose the model you just downloaded.

A new window will appear with configuration options. If you're new to this, leave the settings as they are and click Load Model.

Step 5: Start Chatting

Within seconds the model is up and running, and you can chat with DeepSeek the same way you would with ChatGPT, Claude, or the web version of DeepSeek, except it runs locally with no usage limits. These models are not as capable as their full-size commercial counterparts, but they hold up well for most things.

Conversations are stored only on your computer, so you stay in control. You can delete old chats or start new ones from the sidebar.

LM Studio can also expose a local API, which is handy if you're a developer and want to build against the models.

That's it. You now have DeepSeek running on your own hardware.