llama.cpp reaches version 1.0 for running AI models on your own device

By the GetNews desk · Edited by Sam Calder

The ggml and Hugging Face team released version 1.0 of llama.cpp and ggml, promising clear signals for any change that breaks the interface.

150+model architectures supported

Hype check

Hype2

Real5

Underrated

Quieter than it deserves. This one matters more than the coverage suggests.

Our editorial opinion, based on the sources below. How we score

Your call: hype or real?

Real = it will matter in daily use. Hype = louder than it is. One vote, and it can’t be changed.

Our view and readers’ views are opinions, not statements of fact about a product.

Why it matters

Many local AI apps rely on this tool, and version 1.0 means clearer rules for developers.

For most people

Watch: this tool sits behind many local AI apps.

Version 1.0 came out on 13 November for two libraries: llama.cpp for language models and ggml for machine learning maths.
Any change that breaks the interface will be marked with a new major version number, following semantic versioning.
The tool supports more than 150 model architectures and runs on many kinds of hardware through dedicated backends.
It is available on Linux, Mac, Windows, Android and iOS, and through Homebrew, Winget, Docker and more.
The project is 3.5 years old, and the team says companies such as NVIDIA, AMD, Qualcomm and Intel support hardware testing.

Try itTry it: for developers, a clearer interface and steadier release rules.

The company or lab said it. Primary source linked. Open the sources and check us.

Written with the help of AI tools and checked against the sources above. How we work

See a mistake? Tell us and we’ll fix it.