# llama.cpp release b11784 adds Sycl iq3 crash fix and new binaries

> The open‑source LLM runner llama.cpp updates to b11784 with a crash fix for Sycl iq3 and fresh builds for macOS, iOS, Linux and CUDA.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-b11784-adds-sycl-iq3-crash-fix-and-new-binaries

The ggml‑org team released llama.cpp version b11784. It includes a fix for a crash in the Sycl iq3 backend. The release provides pre‑built binaries for Apple Silicon, Intel Macs, iOS, and various Ubuntu configurations, including Vulkan and CUDA 12.8. The binaries are available for download from the GitHub release page.

## The facts

- Release version b11784 published on 2026‑10‑21
- Adds Sycl iq3 crash fix (#30604) and builds for macOS Apple Silicon, macOS Intel, iOS, Ubuntu x64/arm64/s390x, Vulkan and CUDA 12.8

## Why it matters

Developers can now run llama.cpp on more hardware without crashes, expanding access to local LLM inference.

## Sources & references

1. [ggml-org/llama.cpp b11784](https://github.com/ggml-org/llama.cpp/releases/tag/b11784) – llama.cpp, 2026-10-21

Last updated: 2026-10-21