dougeeai/llama-cpp-python-wheels

Pre-built wheels for llama-cpp-python across platforms and CUDA versions

34
/ 100
Emerging

This project provides pre-built software packages for 'llama-cpp-python,' which is essential for running large language models (LLMs) efficiently on your local computer. It saves you the complex steps of compiling software yourself. You get ready-to-use installation files tailored for your specific NVIDIA GPU, CUDA version, and Python version, enabling you to quickly deploy and experiment with LLMs. This is for AI developers, researchers, or data scientists who want to run powerful LLMs on their own hardware.

Use this if you are a developer using Python, want to run Llama-based large language models on your NVIDIA GPU, and prefer a straightforward installation without manual compilation.

Not ideal if you are not a Python developer, don't use NVIDIA GPUs, or prefer to compile software manually for custom configurations.

AI Development Machine Learning Engineering Large Language Models GPU Acceleration Python Development
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 8 / 25

How are scores calculated?

Stars

40

Forks

3

Language

License

MIT

Last pushed

Nov 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dougeeai/llama-cpp-python-wheels"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.