# llama.cpp release b11747 adds new macOS and Linux binaries

> The open‑source LLM runner llama.cpp posted version b11747 on Oct 20, 2026, with fresh builds for Apple Silicon, Intel Macs and several Ubuntu variants.

Oossa · 2026-10-20 · https://oossa.com/en/llama-cpp-release-b11747-adds-new-macos-and-linux-binaries

The ggml‑org team released llama.cpp version b11747. It ships pre‑compiled binaries for macOS Apple Silicon, macOS Intel, iOS, and multiple Ubuntu builds including CPU, Vulkan and CUDA 12.8. The release also notes a match‑the‑transformers Qwen‑VL resize patch. Users can download the appropriate package from the GitHub release page.

## The facts

- Release date: 2026‑10‑20 ("Tue Oct 20 2026 01:58:12 GMT+0200")
- Binaries now cover macOS arm64, macOS x64, iOS XCFramework, Ubuntu x64/arm64/s390x with CPU, Vulkan and CUDA 12.8

## Why it matters

Developers can run LLaMA models locally on more hardware without building from source.

## Sources & references

1. [ggml-org/llama.cpp b11747](https://github.com/ggml-org/llama.cpp/releases/tag/b11747) – llama.cpp, 2026-10-19

Last updated: 2026-10-20