ggml-org/llama.cpp
llama.cpp
llama.cpp runs large language models locally, from command-line inference to an OpenAI-compatible API server.
Catalog projects marked with #local-ai. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 4 projects with a combined 305,157 GitHub stars. Main languages: C++, Python.
llama.cpp runs large language models locally, from command-line inference to an OpenAI-compatible API server.
GPT4All is a project for running large language models locally on personal computers and inside applications.
Unsloth provides tools and Studio for running and fine-tuning open models locally, with a focus on speed, memory, and practical LLM workflows.