LLamaSharp
A C#/.NET library for efficient local inference of LLaMA and other large language models, based on llama.cpp.
What is LLamaSharp?
LLamaSharp is a C#/.NET library that allows developers to run large language models like LLaMA and LLaVA locally on their devices. It solves the problem of needing cloud-based AI services by providing efficient, offline inference capabilities directly within .NET applications. The library is built on llama.cpp and supports both CPU and GPU acceleration for performance.
.NET developers and engineers who want to integrate local LLM inference into their applications, particularly those focused on privacy, cost reduction, or offline functionality. It's also suitable for AI researchers and hobbyists exploring on-device AI in the .NET ecosystem.
Developers choose LLamaSharp because it brings the performance and flexibility of llama.cpp to the .NET world with a convenient managed API. Its cross-platform support, pre-compiled backends, and integrations with frameworks like Semantic Kernel lower the barrier to entry for local AI development in C#.
Overview
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
Use Cases
Best For
- Building private, offline chatbots within .NET desktop or web applications
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.