# llama.cpp v b11323 release adds new macOS and Linux binaries

> The ggml-org/llama.cpp project posted version b11323 on Oct 1, 2026, with updated binaries for macOS Apple Silicon, Intel, iOS and several Ubuntu builds.

Oossa · 2026-10-01 · https://oossa.com/en/llama-cpp-v-b11323-release-adds-new-macos-and-linux-binaries

The open‑source llama.cpp library released version b11323 on Oct 1 2026. It adds compiled binaries for macOS Apple Silicon, Intel, iOS, and multiple Ubuntu configurations, including CPU, Vulkan and CUDA builds. The release note mentions a HIP tweak for CDNA GPUs. The binaries are available for download from the GitHub release page.

## The facts

- Release date: Oct 1 2026 – "Thu Oct 01 2026 20:45:50 GMT+0200"
- New binaries for macOS Apple Silicon, macOS Intel, iOS, and Ubuntu (CPU, Vulkan, CUDA 12.8)

## Why it matters

Developers can now run llama.cpp locally on more devices, including Macs with Apple Silicon and Ubuntu machines with GPU acceleration.

## Sources & references

1. [ggml-org/llama.cpp b11323](https://github.com/ggml-org/llama.cpp/releases/tag/b11323) – llama.cpp, 2026-10-01

Last updated: 2026-10-01