Newsletter
Join the Community
Subscribe to our newsletter for the latest news and updates
Most popular C/C++ inference engine for LLMs; quantize any Hugging Face model to GGUF and run on CPU, GPU, or Apple Silicon.
Most popular C/C++ inference engine for LLMs; quantize any Hugging Face model to GGUF and run on CPU, GPU, or Apple Silicon.
Open source (MIT).
https://github.com/ggml-org/llama.cpp
https://github.com/ggml-org/llama.cpp
2026-10-13 via OSS AI Hub (ossaihub.com), CC BY 4.0. Editorial notes are short and may lag the vendor site.