https://github.com/angellozan/local_deep_seek

How to run DeepSeek on your local Mac
https://github.com/angellozan/local_deep_seek

ai deepseek deepseek-ai deepseek-chat deepseek-coder deepseek-llm deepseek-r1 open-web vscode vscode-extension

Last synced: 3 days ago
JSON representation

How to run DeepSeek on your local Mac

• Host: GitHub
• URL: https://github.com/angellozan/local_deep_seek
• Owner: AngelLozan
• Created: 2025-02-07T17:42:43.000Z (4 days ago)
• Default Branch: main
• Last Pushed: 2025-02-08T00:54:54.000Z (4 days ago)
• Last Synced: 2025-02-08T01:28:38.953Z (4 days ago)
• Topics: ai, deepseek, deepseek-ai, deepseek-chat, deepseek-coder, deepseek-llm, deepseek-r1, open-web, vscode, vscode-extension
• Homepage:
• Size: 276 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Run DeepSeek Locally with Docker-Compose

Running DeepSeek locally with Docker-Compose is possible with a Mac, though a lighter-weight implementation of the model is recommended.

This will take you through how to run DeepSeek on localhost with a web-ui interface. 

![alt text](image.png) 

AND 

![alt text](image-1.png)



## Steps to run with web interface

1. Install [Ollama](https://martech.org/how-to-run-deepseek-locally-on-your-computer/)

2.  Pick a model based on your hardware:

```

ollama pull deepseek-r1:8b  # Fast, lightweight  

ollama pull deepseek-r1:14b # Balanced performance  

ollama pull deepseek-r1:32b # Heavy processing  

ollama pull deepseek-r1:70b # Max reasoning, slowest

ollama pull deepseek-coder:1.3b # Code completion assist

```

3. Test the model locally via the terminal 

```

ollama run deepseek-r1:8b

```

4. Install [Docker](https://www.docker.com/get-started)

5. Install [Docker-Compose](https://formulae.brew.sh/formula/docker-compose)

6. Create Docker-Compose file as seen in this repo. 

7. Open the docker app and run `docker-compose up -d`

8. Visit `http://localhost:3000` to see your chat. 



## Steps to run with VScode:

1. Once you run steps 1-2 above, you can also install the CodeGPT for VScode extension. 

![alt text](image-2.png)

![alt text](image-3.png)

2. Navigate to the Local LLMs section. This is likely accessed from the initial model selection drop down (pictured with claude selected).

![alt text](image-9.png)

![alt text](image-10.png)

3. From the available options, select 'Ollama' as the local LLM provider.

![alt text](image-11.png)

4. Select your DeepSeek Model and you're done.

![alt text](image-12.png)



## Coming soon: Running Open-webui without locally without internet.