# llama.cpp b12322 release adds memory‑usage tweak

> The open‑source LLaMA inference library updated on 12 Nov 2026 to avoid loading unused graph metadata, saving RAM for developers.

Oossa · 2026-11-12 · https://oossa.com/en/llama-cpp-b12322-release-adds-memory-usage-tweak

The ggml‑org team pushed the b12322 tag for llama.cpp on 12 Nov 2026. The change modifies how graph results reserve metadata, allocating only the needed pages instead of initializing the whole reserve. This reduces the amount of RAM the library touches during inference.

The update is available for all listed platforms, from macOS and Windows CPUs to Linux CUDA, Vulkan and OpenVINO builds.

## The facts

- Release date: 2026-11-12
- Tag: b12322 (commit 4fffab6)

## Why it matters

Developers running LLaMA models on limited‑memory devices will see lower RAM consumption, enabling larger models or smoother multitasking.

## Sources & references

1. [ggml-org/llama.cpp b12322](https://github.com/ggml-org/llama.cpp/releases/tag/b12322) – llama.cpp, 2026-11-12

Last updated: 2026-11-12