# llama.cpp release b11392 adds new binaries and default CI permissions

> The ggml‑org project posted release b11392 on Oct 4, 2026, offering prebuilt binaries for macOS, iOS and several Ubuntu configurations.

Oossa · 2026-10-04 · https://oossa.com/en/llama-cpp-release-b11392-adds-new-binaries-and-default-ci-permissions

On Oct 4, 2026 ggml‑org published llama.cpp version b11392. The update adds ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and multiple Ubuntu builds including CPU, Vulkan and CUDA 12.8. A CI (continuous integration) change sets default permissions for the build process.

## The facts

- Release tag b11392 published Sun Oct 04 2026
- Binaries include macOS arm64, macOS x64, iOS XCFramework, Ubuntu x64 CPU, Ubuntu arm64 Vulkan, Ubuntu x64 CUDA 12.8

## Why it matters

Developers can now download and run llama.cpp on more platforms without compiling it themselves.

## Sources & references

1. [ggml-org/llama.cpp b11392](https://github.com/ggml-org/llama.cpp/releases/tag/b11392) – llama.cpp, 2026-10-04

Last updated: 2026-10-04