# llama.cpp releases version b11465 with new macOS and Linux binaries

> The open‑source LLM inference library adds fresh builds for Apple Silicon, Intel macOS and several Ubuntu configurations.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-releases-version-b11465-with-new-macos-and-linux-binaries

The ggml‑org team published llama.cpp version b11465. It includes pre‑built binaries for macOS Apple Silicon (arm64), macOS Intel (x64), iOS, and multiple Ubuntu flavours (CPU, Vulkan and CUDA 12.8). The release also adds a test change to keep the anchor when testing recurrent rollback. All files are available for download from the GitHub release page.

## The facts

- Release version: b11465
- Published: Wed Oct 07 2026

## Why it matters

Developers can now run LLMs locally on more hardware without compiling the code themselves.

## Sources & references

1. [ggml-org/llama.cpp b11465](https://github.com/ggml-org/llama.cpp/releases/tag/b11465) – llama.cpp, 2026-10-07

Last updated: 2026-10-07