# llama.cpp b12368 improves Hexagon memory handling

> The llama.cpp release updates Hexagon buffer allocation and memory mapping, and provides downloadable builds for several platforms.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-b12368-improves-hexagon-memory-handling

The ggml-org team released llama.cpp b12368 on November 13, 2026. Its listed change improves buffer allocation and memory mapping for Hexagon, including retries for mapping failures and changes intended to reduce memory-address fragmentation.

The release page also offers builds for macOS, iOS and several Linux systems. It does not describe performance gains or specify which devices benefit from the Hexagon changes.

## The facts

- Release: b12368, dated November 13, 2026.
- Downloads include macOS Apple Silicon and Intel builds, an iOS XCFramework, and Ubuntu CPU builds for x64, arm64 and s390x.

## Why it matters

Developers using llama.cpp with Hexagon hardware get updated memory-handling code, but the release notes do not say whether it improves speed or reliability in practice.

## Sources & references

1. [ggml-org/llama.cpp b12368](https://github.com/ggml-org/llama.cpp/releases/tag/b12368) – llama.cpp, 2026-11-13

Last updated: 2026-11-13