BeginnerEdge / Local 9 min read

llama.cpp on Windows with CUDA

Build llama.cpp with NVIDIA GPU support on Windows 11 — the path of least resistance for PC gamers.

Verified stack

Windows 11 · VS Build Tools · CMake · CUDA 12.x · llama.cpp LLAMA_CUDA=ON

Last verified 2026-07-22

Windowsllama.cppCUDAGGUF

Prerequisites

Install Visual Studio Build Tools, CMake, and CUDA Toolkit 12.x.

powershell
winget install Kitware.CMake
# CUDA: download from developer.nvidia.com/cuda-downloads

Build

Enable CUDA backend during CMake configure.

powershell
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
cmake -B build -DLLAMA_CUDA=ON
cmake --build build --config Release -j

Related guides

Deployment guides are educational. Each model is subject to its own license — read the official Hugging Face model card before downloading or deploying.