llama.cpp

Apps & Tools

Video

LLM inference in C/C++ with minimal setup and high performance.

github.com

Built with

Unknown

Build evidence

Strong

Widely recognized, industry-standard open-source project with over 117k stars on GitHub.

Creator

ggml-org @ggml-org

Shipped

2h ago

llama.cpp is a powerful, lightweight framework for running large language models locally on consumer hardware. It optimizes inference across a wide range of architectures, including Apple Silicon, NVIDIA and AMD GPUs, and various CPU instruction sets, using a custom GGML library.

#inference #cpp #quantization #llm

Timeline

Teaser

Video

Playable

Product

Loading…

Media & coverage

sourced from 2 posts

X post by Alok (@analogalok)primaryAlok