# llama.cpp release b12386 adds new binaries and a bug fix

> The open‑source LLM runtime updates with a fix for a masking bug and new pre‑built binaries for macOS, iOS and several Linux platforms.

Oossa · 2026-11-14 · https://oossa.com/en/llama-cpp-release-b12386-adds-new-binaries-and-a-bug-fix

The ggml‑org team published llama.cpp version b12386 on 2026‑11‑14. The update fixes a ‘no‑mask tail’ bug in the hexagon backend. It also ships pre‑compiled binaries for macOS Apple Silicon, macOS Intel, iOS, and a range of Ubuntu builds—including x64, arm64, s390x and Vulkan‑enabled versions.

## The facts

- Release version: b12386
- Published: 2026‑11‑14

## Why it matters

Developers can now download ready‑to‑run llama.cpp binaries for more platforms without building from source.

## Sources & references

1. [ggml-org/llama.cpp b12386](https://github.com/ggml-org/llama.cpp/releases/tag/b12386) – llama.cpp, 2026-11-14

Last updated: 2026-11-14