# llama.cpp release adds OpenCL support for Gemma‑4 GPU decoding

> The Oct 11, 2026 update improves OpenCL performance and enables Gemma‑4 decoding on newer Qualcomm GPUs.

Oossa · 2026-10-11 · https://oossa.com/en/llama-cpp-release-adds-opencl-support-for-gemma-4-gpu-decoding

The llama.cpp library released version b11559 on Oct 11, 2026. It adds OpenCL improvements for faster factor‑allocation and supports Gemma‑4 decoding on Qualcomm E4B and E2B GPUs. The update also optimizes DK64 and DK128 decode paths for various quantisation settings. The changes were co‑authored by Hongqiang Wang of Qualcomm.

## The facts

- Release date: Oct 11, 2026 ("Sun Oct 11 2026 21:14:38 GMT+0200")
- Adds OpenCL Gemma‑4 E4B and E2B GPU decode support

## Why it matters

Developers can now run Gemma‑4 models faster on compatible Qualcomm GPUs, expanding edge‑AI capabilities.

## Sources & references

1. [ggml-org/llama.cpp b11559](https://github.com/ggml-org/llama.cpp/releases/tag/b11559) – llama.cpp, 2026-10-11

Last updated: 2026-10-11