Back to List
TechnologyAIMobileMultimodal

MiniCPM-o: Gemini 2.5 Flash-Level MLLM for Mobile Devices with Vision, Speech, and Full-Duplex Multimodal Live Support

OpenBMB has introduced MiniCPM-o, a new multimodal large language model (MLLM) designed for mobile devices. This model is positioned as a Gemini 2.5 Flash-level equivalent, offering robust capabilities in vision, speech, and full-duplex multimodal live interactions. MiniCPM-o aims to bring advanced AI functionalities directly to users' smartphones, enabling a seamless and interactive experience across various modalities.

GitHub Trending
Share

OpenBMB has unveiled MiniCPM-o, a cutting-edge multimodal large language model (MLLM) specifically engineered for mobile phone applications. This innovative model is touted as achieving a performance level comparable to Gemini 2.5 Flash, signifying its advanced capabilities in processing and understanding diverse data types. MiniCPM-o integrates support for vision, allowing it to interpret and respond to visual inputs, and speech, enabling voice-based interactions. A key feature is its full-duplex multimodal live support, which suggests the model can engage in real-time, continuous, and bidirectional communication across these different modalities. This development aims to enhance the user experience on mobile devices by providing sophisticated AI assistance that can understand and interact with users through a combination of visual and auditory cues in a live setting.

Read Original Article

Related News

Technology

Seerr: Open-Source Media Request and Discovery Manager for Jellyfin, Plex, and Emby Now Trending on GitHub

Seerr, an open-source media request and discovery manager, has gained attention on GitHub Trending. This tool is designed to integrate with popular media servers such as Jellyfin, Plex, and Emby, providing users with enhanced capabilities for managing and discovering media content. The project is developed by the seerr-team and was published on February 18, 2026.

Technology

Nautilus_Trader: High-Performance Algorithmic Trading Platform and Event-Driven Backtester Trends on GitHub

Nautilus_Trader, developed by nautechsystems, is gaining traction on GitHub Trending as a high-performance algorithmic trading platform. It also features an event-driven backtester, providing a robust solution for developing and testing trading strategies. The project, published on February 18, 2026, is accessible via its GitHub repository.

Technology

gogcli: Command-Line Interface for Google Suite - Manage Gmail, GCal, GDrive, and GContacts from Your Terminal

gogcli is a new command-line interface (CLI) tool designed to bring the power of Google Suite directly to your terminal. Developed by steipete, this utility allows users to manage various Google services, including Gmail, Google Calendar (GCal), Google Drive (GDrive), and Google Contacts (GContacts), all from a unified command-line environment. The project, trending on GitHub, aims to provide a streamlined way to interact with essential Google services without leaving the terminal.