# llama.cpp release b11481 adds Cohere2 vision support

> The open‑source llama.cpp library now supports Cohere2 vision models and ships new binaries for macOS, iOS and Ubuntu.

Oossa · 2026-10-08 · https://oossa.com/en/llama-cpp-release-b11481-adds-cohere2-vision-support

The ggml‑org team released llama.cpp version b11481 on 2026‑10‑08. The update adds support for Cohere2 vision models and includes pre‑built binaries for Apple Silicon, Intel macOS, iOS and several Ubuntu configurations. The files are available for download from the GitHub release page.

## The facts

- Release version: b11481
- Release date: 2026‑10‑08

## Why it matters

Developers can now run image‑aware AI models locally on macOS, iOS and Linux without cloud services.

## Sources & references

1. [ggml-org/llama.cpp b11481](https://github.com/ggml-org/llama.cpp/releases/tag/b11481) – llama.cpp, 2026-10-08

Last updated: 2026-10-08