# inclusionAI Debuts 'Any-to-Any' Multimodal MoE Model

> The new Ming-flash-omni-Preview aims to handle any combination of data modalities using an efficient Mixture of Experts architecture.

Published by The Open Weights on Oct 14, 2025. Canonical: https://theopenweights.com/news/ming-flash-omni-ruk4

## Key facts

- Company: inclusionAI
- Model: Ming-flash-omni-Preview
- Version: flash-omni Preview
- Category: Any-to-Any
- Modalities: Any-to-Any
- License: MIT (Open weights, commercial use allowed)
- Active parameters: 6B
- Context window: 33K tokens
- Architecture: BailingMM2NativeForConditionalGeneration
- Precision: BF16
- Weights size: 208.8 GB
- Significance: notable
- Published: 2025-10-14
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/inclusionAI/Ming-flash-omni-Preview
- Canonical URL: https://theopenweights.com/news/ming-flash-omni-ruk4

AI research group inclusionAI has released Ming-flash-omni-Preview, a new open-source model designed for true multimodal flexibility. Released under a permissive MIT license, the model pursues an "any-to-any" capability, meaning it's built to process and generate a wide combination of data types, not just text and images.

This approach, often called "omnimodal," represents a significant step beyond models that are limited to specific input-output pairs, like text-to-image or audio-to-text. An any-to-any system can theoretically accept a mix of inputs—say, an image, a line of text, and an audio clip—and generate a relevant output in a requested modality.

The model is built on a Mixture of Experts (MoE) architecture, a technique that improves computational efficiency by routing inputs to specialized subnetworks, or "experts," rather than engaging the entire model for every token. According to the release card, Ming-flash-omni is based on a previous model called Ling-flash-2.0.

As major labs pursue closed, highly capable omnimodal models, the release of an open alternative like [Ming-flash-omni-Preview](https://huggingface.co/inclusionAI/Ming-flash-omni-Preview) provides researchers and developers with a valuable tool for experimentation. While labeled as a preview, it offers a foundational component for building applications that require a more fluid and comprehensive understanding of diverse data streams.

## Get the model

- [Hugging Face](https://huggingface.co/inclusionAI/Ming-flash-omni-Preview)

## Sources

- [inclusionAI/Ming-flash-omni-Preview](https://huggingface.co/inclusionAI/Ming-flash-omni-Preview) — Hugging Face, Oct 14, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "inclusionAI Debuts 'Any-to-Any' Multimodal MoE Model", The Open Weights, Oct 14, 2025, https://theopenweights.com/news/ming-flash-omni-ruk4