Biolm-3B

Biolm-3B (originally Qwen2.5-Omni-3B) is a 3-billion-parameter end-to-end multimodal large language model.

About

Biolm-3B is designed for research on cross-modal temporal grounding and audio-visual understanding. It accepts text, images, audio, and video as input, and can generate both text and natural speech as output in a streaming manner.

Modalities

Modality	Input	Output
Text	Yes	Yes
Image	Yes	—
Audio	Yes	Yes
Video	Yes	—

Intended Use

This model is intended for academic research on multimodal temporal reasoning, cross-modal attention analysis, and audio-visual language modeling.