The server is always busy? DeepSeek-R1 local deployment graphic tutorial is here

Recently, the domestic large-scale model DeepSeek-R1 has rapidly risen in the market and has become a new favorite of many users. However, with the sharp increase in its popularity and number of users, the server is frequently busy.

In order to get rid of the trouble of busy servers, local deployment of DeepSeek-R1 has become an excellent solution, which not only reduces the dependence on network connection, but also enhances data security. Next, let's take a look at how to operate it.

1. Download and install Ollama

Ollama is an open source localized large model deployment tool. Users can use Ollama to easily install, configure and run various open source large models.

‌Go to the Ollama official website (URL: https://ollama.com/download). The platform supports macOS, Linux, and Windows systems. Select the corresponding version to download according to the computer system.

Taking the Macbook Air used by the editor as an example, select "macOS" and click Download.

Once the download is complete, double-click the installer and follow the prompts to complete the installation. If you see the llama icon in the top menu bar, Ollama is running.

2. Install DeepSeek-R1

Next, we go back to the Ollama official website, find “Models” in the upper left corner and click to enter.

Enter deepseek-r1 in the search box, find "deepseek-r1", and click to enter the details page.

DeepSeek-R1 has many types. The 1.5B, 7B, 14B, etc. following each type name are the parameters of the model. You can choose the parameters according to the hardware configuration of your computer.

(Above: Features of each version of DeepSeek-R1)

It should be noted that the number of model parameters is positively correlated with the complexity of processing data and generating content. As the number of parameters increases, the model has the ability to process more complex data, and the generated content is correspondingly richer and more diverse, but the hardware configuration requirements for the computer are also higher.

The editor chose version 8b and copied the "ollama run deepseek-r1:8b" command.

Bring up the computer's "Launchpad", search for "Terminal" and click to enter, paste the command into the "Terminal" window, press Enter, and wait for the installation to complete.

3. Download and install Chatbox

Chatbox is an intelligent conversation tool that combines artificial intelligence technology and a convenient operating interface. It supports Windows, MacOS, Linux, Android, iOS and web terminals, and can help users complete tasks quickly.

Go to the Chatbox official website (https://chatboxai.app/zh), find the version suitable for your computer system, download and complete the installation.

After the download is complete, open Chatbox, click "Settings", and select "OLLAMA API" in "Model Provider".

In the "Model" list, select the installed "deepseek-r1:8b" and click "Save".

After completing the above three steps, you can start a conversation with DeepSeek-R1 in the Chatbox.

In conclusion:

As artificial intelligence is developing rapidly, learning to use large models will undoubtedly give us an advantage in information processing and knowledge acquisition. I believe that everyone can fully explore the potential of DeepSeek-R1 and create more results during use.

Source: Chongqing Tianji Network Co., Ltd.

Audit expert: Li Zhigao, senior engineer/President of Chongqing Tianji Network Co., Ltd.

Statement: Except for original content and special notes, some pictures are from the Internet. They are not for commercial purposes and are only used as popular science materials. The copyright belongs to the original authors. If there is any infringement, please contact us to delete them.