# llama.cpp adds Muse Spark Open multimodal model

> The open‑source llama.cpp library now includes Muse Spark Open, a model that handles text, images and audio.

Oossa · 2026-10-16 · https://oossa.com/en/llama-cpp-adds-muse-spark-open-multimodal-model

On 2026-10-16 the ggml‑org/llama.cpp project released version b11671. The update adds Muse Spark Open, a multimodal model that can process text, vision and audio inputs. It uses a mixture‑of‑experts architecture with 256 experts and supports 8‑way routing. Vision reuses the Muse Glimmer tower and audio is handled by a four‑stage causal convolutional pyramid. The code changes were contributed by Xuan Son Nguyen, Pedro Cuenca and Sigbjørn Skjæret.

## The facts

- Muse Spark Open model added in llama.cpp release b11671
- Release date: 2026-10-16

## Why it matters

Developers can now run a single open‑source model for text, image and audio tasks on local hardware.

## Sources & references

1. [ggml-org/llama.cpp b11671](https://github.com/ggml-org/llama.cpp/releases/tag/b11671) – llama.cpp, 2026-10-16

Last updated: 2026-10-16