# OpenBMB Releases 'Any-to-Any' Multimodal Model

> The new MiniCPM-o 4.5 model from the open-source research group can process and generate interleaved combinations of images, text, and audio.

Published by The Open Weights on Feb 3, 2026. Canonical: https://theopenweights.com/news/minicpm-o-4-5-xb5m

## Key facts

- Company: OpenBMB
- Model: MiniCPM-o 4.5
- Version: 4.5
- Category: Any-to-Any
- Modalities: Any-to-Any, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Context window: 41K tokens
- Architecture: MiniCPMO
- Precision: BF16
- Weights size: 18.7 GB
- Significance: notable
- Published: 2026-02-03
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/openbmb/MiniCPM-o-4_5
- Canonical URL: https://theopenweights.com/news/minicpm-o-4-5-xb5m

The open-source AI community OpenBMB has released MiniCPM-o 4.5, a new model that significantly expands the possibilities for multimodal interaction. Unlike many models that process one type of input to produce a single type of output, MiniCPM-o is designed for "any-to-any" communication, capable of handling a mix of text, images, and audio in a single conversational flow.

This approach aims to create more natural and fluid interactions with AI. The model's "full-duplex" support suggests it can understand interleaved inputs—for example, a user could provide an image, ask a question in text, and follow up with a spoken clarification. In response, the model could generate its own combination of text, a new image, and synthesized speech.

## Why It Matters

This release represents a move beyond simple, turn-based tasks like image captioning. It points toward AI systems that can participate in dynamic, multi-format conversations. By handling various data streams simultaneously, MiniCPM-o could power more sophisticated applications in areas like:

*   Interactive educational tools
*   Advanced accessibility software
*   Complex creative and design assistants

While technical details like parameter count were not specified in the release record, the model's architecture itself is the key development. Researchers can explore its capabilities directly, as it is [available on Hugging Face](https://huggingface.co/openbmb/MiniCPM-o_4_5). The model provides an open-source foundation for building the next generation of conversational AI agents.

## Get the model

- [Hugging Face](https://huggingface.co/openbmb/MiniCPM-o-4_5)

## Sources

- [openbmb/MiniCPM-o-4_5](https://huggingface.co/openbmb/MiniCPM-o-4_5) — Hugging Face, Feb 3, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "OpenBMB Releases 'Any-to-Any' Multimodal Model", The Open Weights, Feb 3, 2026, https://theopenweights.com/news/minicpm-o-4-5-xb5m