Chinese AI model – DeepSeek AI has quickly gained immense popularity, surpassing OpenAI’s ChatGPT on the App Store for a while. With its innovative approach to artificial intelligence and advanced capabilities, it has captured the attention of tech enthusiasts and AI developers alike.
DeepSeek R1 is an open-source AI model licensed by the Massachusetts Institute of Technology (MIT), making it accessible to anyone.It is currently available primarily for research purposes. Its open-source nature allows for extensive customization and allows one to freely use DeepSeek R1 for both personal and professional projects. To use DeepSeek on your computer, you will need to follow a series of steps to install, configure, and start using the platform. Here’s a detailed guide on how to get started with DeepSeek:
Check system requirements
Before you begin the installation process, ensure that your computer meets the system requirements. Since DeepSeek involves heavy data processing and potentially AI model training, having a high-performance machine is important. Here are general requirements:
Operating System:
- Windows 10 or later
- macOS 10.15 or later
- Linux (Ubuntu 18.04 or later)
Hardware Requirements:
- CPU: Multi-core processor (Quad-core or higher recommended)
- GPU: High-performance GPU (NVIDIA with CUDA support is typically required for AI tasks)
- RAM: Minimum 8GB (16GB or more recommended for AI-related tasks)
- Storage: SSD with at least 50GB free space (more space required for handling large datasets)
Software Dependencies:
- Python (for model training and scripting)
- CUDA Toolkit (for GPU acceleration)
- Required deep learning libraries (e.g., TensorFlow, PyTorch)
Download DeepSeek Software
There are several models of R1 to choose from, ranging from 1.5 billion to 70 billion parameters.
DeepSeek R1 costs approximately ₹684 per million tokens. With Ollama, you can avoid the hassle of cloud subscriptions. Here’s a step-by-step guide on how to install and set up DeepSeek on your Windows computer using Ollama:
- Go to the official Ollama website and download the Windows installer.
- Double-click the installer and follow the on-screen prompts.
- Make sure you have at least 4GB of free storage space before proceeding.
- Once installed, open Command Prompt on your computer.
- Enter the following command to start the application with debug mode enabled: $env:OLLAMA_DEBUG=”1″ & “ollama app.exe”
- Where your data and logs are stored:
– Logs and Updates: %LOCALAPPDATA%\Ollama
– Program Files: %LOCALAPPDATA%\Programmes\Ollama
– Models and Settings: %HOMEPATH%.ollama
Mac users, on the other hand, can directly download the installer from the official Ollama website. Alternatively, if you’re familiar with Homebrew, you can use the following command to install Ollama: brew install ollama.
How to use DeepSeek
To start using DeepSeek, open the Terminal app. Once it’s open, type the following command: ollama run deepseek-r1:8b.
Press Enter to run the command, and DeepSeek R1 will start up, allowing you to interact with the model through the terminal interface. With this, you’ll have access to DeepSeek’s AI features.
How to access DeepSeek on web
In case you do not wish to download the software, you can simply access the AI model on web.
- Simply head to https://chat.deepseek.com/sign_in
- Here you will be asked to register using your email id/ number. Alternatively, you can also register using Google account.
- Once registered, you can start interacting with the chatbot.
Do note that the new registrations are currently put on hold. The website reads “Due to large-scale malicious attacks on DeepSeek’s services, registration may be busy. Please wait and try again. Registered users can log in normally. Thank you for your understanding and support.”
How to use DeepSeek on mobile
DeepSeek app is available on Apple App Store. Open App Store on your iPhone>Type DeepSeek in the search bar and tap on Install. You can register on the app by setting up email ID and password.