# llama.cpp releases new binaries for macOS, Linux and iOS

> The open‑source LLM runtime adds prebuilt binaries for Apple Silicon, Intel Macs, iOS and several Ubuntu builds, including Vulkan and zDNN support.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-releases-new-binaries-for-macos-linux-and-ios-4553748

ggml‑org released llama.cpp version b12370 on 2026‑11‑13. The update ships ready‑to‑run binaries for macOS Apple Silicon, Intel Macs, iOS and a range of Ubuntu systems. Linux builds now include Vulkan GPU support and a zDNN‑enabled s390x package. The release also adds a CUDA‑HIP tuning tweak for AMD GPUs.

## The facts

- Release tag b12370 published on 2026‑11‑13
- Prebuilt binaries for macOS arm64, macOS x64, iOS, Ubuntu x64, arm64, s390x (CPU, Vulkan, zDNN)

## Why it matters

Developers can run Llama models locally on more platforms without building from source.

## Sources & references

1. [ggml-org/llama.cpp b12370](https://github.com/ggml-org/llama.cpp/releases/tag/b12370) – llama.cpp, 2026-11-13

Last updated: 2026-11-13