Rhino-2.6

Rhino-2.6 (originally MiniCPM-o-2.6) is an 8-billion-parameter end-to-end multimodal large language model with real-time speech conversation and live streaming capabilities.

About

Rhino-2.6 is designed for research on cross-modal temporal grounding and audio-visual understanding. It supports vision, speech, real-time speech conversation, multimodal live streaming, and end-to-end voice cloning. It processes images up to 1.8 million pixels in any aspect ratio.

Modalities

Modality Input Output
Text Yes Yes
Image Yes β€”
Audio Yes Yes
Video Yes β€”

Intended Use

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

Downloads last month
404
Safetensors
Model size
9B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support