TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

MiniCPM-o 4.5

By OpenBMB
MiniCPM-o is OpenBMB’s series of on-device multimodal LLMs upgraded from MiniCPM-V. The 4.5 model takes text, images, video and audio and outputs both text and speech in an end-to-end way, with about 9B total parameters and performance comparable to Gemini 2.5 Flash on vision and speech tasks. Its full-duplex streaming means incoming video/audio and outgoing speech/text do not block each other, enabling real-time assistants that can watch, listen and talk simultaneously on phones and PCs.
New Multimodal Gen 3
Released: August 26, 2025

Overview

MiniCPM-o 4.5 is an on-device multimodal LLM (~9B params) that matches Gemini 2.5 Flash on vision and speech, supporting full-duplex live streaming so it can see, listen and speak in real time.

About OpenBMB

OpenBMB is short for Open Lab for Big Model Base. The goal of OpenBMB is to build the model base and toolkit for large-scale pre-trained language models.

Website: openbmb.cn
View Company Profile

Tools using MiniCPM-o 4.5

No tools found for this model yet.

Last updated: February 25, 2026
0 AIs selected
Clear selection
#
Name
Task