To run DeepSeek on Windows with a WebUI, you need to install Ollama, text-generation-webui, or another UI like Gradio. Below is the hardware requirement table for all model sizes.

DeepSeek WebUI Hardware Requirements

ModelVRAM (GPU)RAM (System)CPUStorage (SSD/NVMe)Recommended GPU
1.5B4GB+16GBIntel i5 / Ryzen 550GBNVIDIA RTX 2060
7B16GB+32GBIntel i7 / Ryzen 7100GBNVIDIA RTX 3090 / 4090
8B24GB+64GBIntel i9 / Ryzen 9150GBNVIDIA RTX 4090 / A100
14B32GB+128GBIntel i9 / Ryzen 9200GBNVIDIA A100 (40GB)
32B48GB+256GBAMD EPYC / Xeon400GBNVIDIA H100 (80GB)
70B80GB+512GBAMD EPYC / Xeon1TB2× NVIDIA H100 (80GB)
671B512GB+ (Multiple GPUs)1.5TB+AMD EPYC / Xeon10TB+8× NVIDIA H100 (80GB)

Installation Steps for DeepSeek with WebUI on Windows

Option 1: Using text-generation-webui

  1. Install Dependencies
  • Install Python 3.10+
  • Install CUDA Toolkit 11.8+ (for NVIDIA GPUs)
  • Install Git
  1. Download text-generation-webui
   git clone https://github.com/oobabooga/text-generation-webui.git
   cd text-generation-webui
  1. Create Virtual Environment & Install Dependencies
   python -m venv venv
   venv\Scripts\activate
   pip install -r requirements.txt
  1. Download a DeepSeek Model (Example: 7B)
  • Download DeepSeek-7B GGUF model from Hugging Face:
    https://huggingface.co/
  • Place the downloaded model in text-generation-webui/models/deepseek-7b
  1. Launch WebUI
   python server.py --model deepseek-7b
  • Open http://localhost:5000 in your browser.

Option 2: Using Ollama

Ollama provides an easy way to run DeepSeek with WebUI.

  1. Install Ollama: https://ollama.com
  2. Download & Run DeepSeek Model
   ollama run deepseek
  1. Access WebUI:
  • Go to http://localhost:11434

Notes:

  • 1.5B – 8B models can run on high-end gaming GPUs (RTX 3090/4090).
  • 14B+ models need professional AI hardware (A100, H100).
  • 32B+ models require multiple GPUs with tensor parallelism.
  • 671B model is too large for local use (requires cloud clusters).

- 3
Was this article helpful?
YesNo

Similar Posts

How to install deep security agent on windows

ByTeam

1. Prerequisites Before installing the Deep Security Agent, ensure the following: 2. Installation Steps Step 1: Download the Installer Step 2: Run the Installer Step 3: Follow the Installation Wizard Step 4: Complete Installation 3. Post-Installation After installation: 4. Silent Installation (Optional) For automated installations, you can use a silent install method. Steps: 5. Troubleshooting…

DeepSeek Coder V2 requirements

ByTeam

DeepSeek-Coder-V2 is an open-source Mixture-of-Experts (MoE) code language model available in two configurations: Both models support a context length of 128,000 tokens. citeturn0search0 The hardware requirements for these models are not explicitly detailed in the official documentation. However, based on the model sizes and typical resource needs for similar large-scale language models, the following table…

deepseek coder v2 lite vs codestral

ByTeam

DeepSeek Coder V2 Lite vs Codestral 25.01: A Comprehensive Comparison DeepSeek Coder V2 Lite and Codestral 25.01 are both advanced language models designed to assist with code generation and understanding. Each model has its own strengths, depending on the user’s needs. Below is a detailed comparison that highlights their features, performance, and other key aspects…

GPU Requirements Guide for DeepSeek Models

ByTeam

DeepSeek models represent the frontier of large language model (LLM) advancements, delivering exceptional performance across various domains. However, due to their computational demands, selecting the right hardware configuration is paramount to unlock their full potential. This guide will help you navigate system requirements, VRAM needs, GPU recommendations, and performance optimizations tailored for different DeepSeek model…

Running DeepSeek-R1 Locally with Ollama and Docker

ByTeam

Introduction Running AI models like DeepSeek-R1 locally can be both an exciting learning experience and a powerful way to leverage AI capabilities without relying on cloud-based solutions. In this guide, we’ll explore two different methods for running DeepSeek-R1: By following these steps, you’ll be able to interact with DeepSeek-R1 in no time! DeepSeek-R1 Model Requirements…