FreeLLMllama.cpp releases version 1.0.0 with new libraries and broader hardware support
The open‑source llama.cpp project launches v1.0.0, adding libllama and libggml libraries and expanding platform compatibility.
On November 13, 2026 the llama.cpp team announced version 1.0.0, marking the first major release that introduces breaking changes to the public C API.
The release bundles two libraries: libllama for LLM inference in C/C++ and libggml, a tensor library for machine learning, both with updated public headers.
Version 1.0.0 adds pre‑release artifacts for Linux, macOS, Windows, Android and iOS, and is distributed through Docker, Homebrew, conda‑forge, Winget, MacPorts and XCFramework.
The team emphasizes stricter semantic versioning, with MAJOR bumps indicating API incompatibility, and notes ongoing investment in CI infrastructure and community contributions.
Ce que cela signifie pour vous
The update gives developers a stable, cross‑platform foundation for building private AI applications, especially those that run locally. Users seeking free or on‑device models benefit from broader hardware compatibility and the ability to run multi‑modal LLMs without cloud services.
Sources
- llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem, Hugging Face (official), 13 Nov 2026
Rédigé automatiquement à partir des sources ci‑dessus, puis vérifié par notre code : chaque nombre et chaque nom doivent y figurer, et aucune phrase ne doit copier une source. Une erreur ? Signalez‑la.
Quelle IA pouvez‑vous utiliser gratuitement aujourd’hui ?
Tous les modèles IA gratuits, classés par votes humains anonymes, avec la mémoire et la vitesse dont ils ont besoin sur votre propre GPU.