# llama.cpp release b12361 adds new binaries and moves MOE cache code

> The open‑source llama.cpp project posted version b12361 on Nov 13 2026, offering fresh macOS, iOS and Ubuntu binaries and restructuring its MOE‑cache code.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-release-b12361-adds-new-binaries-and-moves-moe-cache-code

The ggml‑org team released llama.cpp version b12361. The update moves the MOE‑cache code out of the internal graph handling and provides new pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu flavors, including CPU and Vulkan builds. A KleidiAI‑enabled macOS Apple Silicon binary is listed but currently disabled. All files are available for download from the GitHub release page.

## The facts

- Version b12361 released on 2026-11-13
- Binaries include macOS arm64, macOS Intel, iOS XCFramework, and Ubuntu x64/arm64 CPU and Vulkan builds

## Why it matters

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

## Sources & references

1. [ggml-org/llama.cpp b12361](https://github.com/ggml-org/llama.cpp/releases/tag/b12361) – llama.cpp, 2026-11-13

Last updated: 2026-11-13