# llama.cpp b11913 adds a Hexagon memory-size setting

> The llama.cpp release adds an override for Hexagon’s VTCM size, with values that can use K, M or G suffixes.

Oossa · 2026-10-27 · https://oossa.com/en/llama-cpp-b11913-adds-a-hexagon-memory-size-setting

The ggml-org team’s llama.cpp b11913 release adds a configurable size override for VTCM, a memory resource used by the Hexagon backend. The setting is named `GGML_HEXAGON_VTCM_SIZE` and accepts K, M or G suffixes.

The release notes also show that a proposed `NTHREADS` cap was later dropped. They do not give a default VTCM size or explain how the change affects performance.

## The facts

- The setting is `GGML_HEXAGON_VTCM_SIZE`.
- Accepted size suffixes include K, M and G.

## Why it matters

People running llama.cpp with Hexagon hardware can override the VTCM size, but the release notes do not say what value they should use or whether it improves performance.

## Sources & references

1. [ggml-org/llama.cpp b11913](https://github.com/ggml-org/llama.cpp/releases/tag/b11913) – llama.cpp, 2026-10-27

Last updated: 2026-10-27