# inclusionAI's Ming 2.0 Tackles Any-to-Any Multimodality

> The new open-source Mixture-of-Experts model can process and generate content across text, images, and audio in any combination.

Published by The Open Weights on Feb 10, 2026. Canonical: https://theopenweights.com/news/ming-flash-omni-2-0-bg44

## Key facts

- Company: inclusionAI
- Model: Ming-flash-omni 2.0
- Version: 2.0
- 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: 208.5 GB
- Significance: notable
- Published: 2026-02-10
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/inclusionAI/Ming-flash-omni-2.0
- Canonical URL: https://theopenweights.com/news/ming-flash-omni-2-0-bg44

AI research group inclusionAI has released Ming-flash-omni 2.0, an ambitious open-source model designed to natively handle text, images, and audio. Released under a permissive MIT license, the model aims to provide a single, unified system for 'any-to-any' multimodal tasks.

Unlike many multimodal models that primarily link text and images, Ming 2.0 is built to process and generate content across all three modalities interchangeably. This could enable capabilities like generating an image from an audio clip, describing a picture with spoken words, or transcribing speech, all within one framework.

The model utilizes a Mixture-of-Experts (MoE) architecture, a design that can lead to more efficient computation by only activating relevant parts of the network for a given task. While specific details on its parameter count and training data are not yet public, the MoE approach suggests a focus on scalable performance.

This release represents another step forward for complex, open-source AI systems that can perceive and create in ways more analogous to human senses. Researchers and developers can explore the model's capabilities on its [Hugging Face repository](https://huggingface.co/inclusionAI/Ming-flash-omni-2.0).

## Get the model

- [Hugging Face](https://huggingface.co/inclusionAI/Ming-flash-omni-2.0)

## Sources

- [inclusionAI/Ming-flash-omni-2.0](https://huggingface.co/inclusionAI/Ming-flash-omni-2.0) — Hugging Face, Feb 10, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "inclusionAI's Ming 2.0 Tackles Any-to-Any Multimodality", The Open Weights, Feb 10, 2026, https://theopenweights.com/news/ming-flash-omni-2-0-bg44