llama.cpp is an open source C++ project by ggml-org, created in March 2023. It has 131,913 stars and 24,640 forks on GitHub and is released under the MIT license. Its most recent commit was on Oct 21, 2026, and it has 793 open issues, 17 of them labelled “good first issue”, which makes it a friendly place to start contributing. Its GitHub topics include ggml. On FindOpenSource.dev it is listed under LLMs.
131,913 stars today
The chart fills in as we take a snapshot every day.
by ollama
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
by huggingface
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
by open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
