ggml-org/llama.cpp
C/C++ inference engine for LLMs and MLLMs
- Chart
- Not on a chart right now
- Stars
- 135.6k
What it is
Built on top of the ggml library, llama.cpp enables LLM and MLLM inference with minimal setup across a wide range of hardware.
Who it is for
Developers who want to run language models locally or in the cloud, or host an OpenAI-compatible API server.
Why it is trending
It recently published its v1.0.0 release and gained 4,449 stars today.
Main features
- Direct model download and CLI execution from Hugging Face
- OpenAI-compatible API server with built-in Llama Chat
- Support for multimodal (VLM), TTS, and GBNF grammars
- Multiple installation options including Docker and pre-built binaries
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary