1. X
  2. OpenBMB
Log inSign up
OpenBMB
1,336 posts
OpenBMB profile banner
user avatar

OpenBMB

@OpenBMB
OpenBMB (Open Lab for Big Model Base) aims to build foundation models and systems towards AGI. Connect with us: discord.gg/7q3ry8Ny8K
huggingface.co/openbmb
Joined February 2022
371
Following
8,915
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    OpenBMB
    @OpenBMB
    Jul 19
    🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕
    Image
    00:00
  • user avatar
    OpenBMB
    @OpenBMB
    20h
    Developer @jaxxchen003 built Digital Human Video Production, an open-source workflow for creating AI-powered digital human videos.👍 Powered by VoxCPM2, this project brings voices and digital humans together, enabling natural voice cloning, expressive speech generation, and
    Image
  • user avatar
    OpenBMB
    @OpenBMB
    Aug 18
    Great to see the community pushing MiniCPM5-1B inference further!🥳 @VukRosic99 has open-sourced an FP8 serving optimization that achieves significant speedups on RTX 3060 without modifying the official checkpoint. The reproducible benchmarks and practical exploration of
    user avatar
    Vuk Rosić 武克
    @VukRosic99
    Aug 17
    My AI startup made an LLM nearly 80% faster. An autonomous research system took MiniCPM5-1B from about 165 to 287 tokens/second on an RTX 3060. I show what worked, what failed, and why AI that optimizes AI could become a real business. Become an AI researcher with courses and
    Image
    00:00
  • user avatar
    OpenBMB
    @OpenBMB
    Aug 18
    Great walkthrough of MiniCPM-o 4.5 by @LearnOpenCV! Unlike traditional turn-based multimodal systems, MiniCPM-o 4.5 is designed for real-time, full-duplex interaction — processing live video, incoming audio, and generating speech responses simultaneously. Its unified pipeline
    user avatar
    Satya Mallick
    @LearnOpenCV
    Aug 12
    1/6 🧵 MiniCPM-o 4.5 is a 9B open-source model built to see live video, hear incoming audio, and speak at the same time. In this video, we explain how full-duplex multimodal AI works—and show the LearnOpenCV experiments.
    Image
    00:00
  • user avatar
    OpenBMB
    @OpenBMB
    Aug 17
    🧠 What if you could debate with history’s greatest thinkers — and hear them argue back? Meet The Grand Tribunal by @zirmythen, an Ace Attorney-style AI debate game where you challenge legendary philosophers like Oscar Wilde, Nietzsche, Plato, and Schopenhauer. ⚔️ Enter the
    Image

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement