# llama.cpp release b11486 adds more accurate GELU activation

> The open‑source llama.cpp library released version b11486 on Oct 8 2026, improving GELU activation accuracy and adding new binaries for macOS, iOS and Linux.

Oossa · 2026-10-08 · https://oossa.com/en/llama-cpp-release-b11486-adds-more-accurate-gelu-activation

The ggml‑org team published llama.cpp version b11486 on Oct 8 2026. The update improves the accuracy of the GELU activation function, a small math piece used in many language models. It also provides pre‑built binaries for Apple Silicon, Intel macOS, iOS, and several Ubuntu configurations (CPU, Vulkan, CUDA). The binaries can be downloaded directly from the release page.

## The facts

- Version b11486 released on 2026‑10‑08
- Adds improved GELU accuracy and new macOS, iOS, Ubuntu binaries

## Why it matters

Developers can run LLaMA models faster and with more precise calculations on their own machines.

## Sources & references

1. [ggml-org/llama.cpp b11486](https://github.com/ggml-org/llama.cpp/releases/tag/b11486) – llama.cpp, 2026-10-08

Last updated: 2026-10-08