# llama.cpp release b11739 adds new binaries and Jinja filter

> The ggml-org/llama.cpp project published version b11739 on Oct 19 2026, offering updated binaries for macOS, iOS, and various Linux platforms.

Oossa · 2026-10-19 · https://oossa.com/en/llama-cpp-release-b11739-adds-new-binaries-and-jinja-filter

The open‑source llama.cpp library released version b11739 on Oct 19 2026. The update adds a Jinja template ‘unique’ filter and fixes alignment issues. Pre‑built binaries are now available for macOS Apple Silicon, Intel, iOS, and several Ubuntu configurations, including CPU, Vulkan and CUDA‑12 builds. Users can download the appropriate archive from the GitHub release page.

## The facts

- Release version b11739 published on 2026-10-19
- Binaries provided for macOS (arm64, x64), iOS, and Ubuntu (x64, arm64, s390x) with CPU, Vulkan and CUDA‑12 options

## Why it matters

Developers can run llama.cpp locally on more devices without building from source, speeding up experimentation.

## Sources & references

1. [ggml-org/llama.cpp b11739](https://github.com/ggml-org/llama.cpp/releases/tag/b11739) – llama.cpp, 2026-10-19

Last updated: 2026-10-19