# llama.cpp release b11471 adds new tokens and binaries

> The open‑source llama.cpp library ships version b11471 with extra vocabulary tokens and pre‑built binaries for macOS, iOS and Linux.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-release-b11471-adds-new-tokens-and-binaries

The ggml‑org team released llama.cpp version b11471. It adds a new set of 30090 plamo fim tokens to the model vocabulary. The release also provides ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and several Linux builds (CPU, Vulkan, CUDA 12.8). Users can download the appropriate package from the GitHub release page.

## The facts

- Version: b11471
- Release date: 2026-10-07

## Why it matters

Developers can now run llama.cpp locally on more devices without building from source, saving time and simplifying testing.

## Sources & references

1. [ggml-org/llama.cpp b11471](https://github.com/ggml-org/llama.cpp/releases/tag/b11471) – llama.cpp, 2026-10-07

Last updated: 2026-10-07