MiniCPM-o 4.5

What it does

A 9B omni-modal model that sees, listens, and speaks simultaneously. Features full-duplex streaming (no turn-taking lag) and proactive interaction. Outperforms GPT-4o on vision benchmarks. Runs locally via llama.cpp & Ollama.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone [2026.02.06] 🥳 🥳 🥳 We open-sourced a realtime web demo deployable on your own devices like Mac or GPU. Try it now ! MiniCPM-o 4.5 is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include: 🔥 Leading Visual Capability. MiniCPM-o 4.5 achieves an average score of 77.6 on OpenCompass, a…from huggingface.co

• 
  Ollama multimodal engine2025 · ollama.com · ▲277

  Run leading vision models locally with the new engine

• 
  MiniCPM-V 4.52025 · huggingface.co · ▲93

  GPT-4o level vision model on the phone

• 
  MiniCPM-V 4.6May 2026 · github.com · ▲98

  Ultra-efficient 1.3B vision-language model for mobile

• 
  MiniCPM 4.12025 · huggingface.co · ▲116

  The on-device model for your personal data

• 
  MiniCPM5-1BMay 2026 · huggingface.co · ▲96

  A new SOTA for compact open models on the edge

• 
  OpenAI GPT-4o Audio Models2025 · openai.com · ▲379

  Build Powerful Voice Agents

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• 
  Rork Max▲1,428

  Best AI for iOS apps. Website that replaces Xcode

  Life & fun · Feb 2026 · rork.com

• 
  happycapy▲1,365

  The agent-native computer, for the rest of us

  AI · Feb 2026 · happycapy.ai

• 
  SuperX▲897

  All-in-one growth OS for serious 𝕏 creators

  AI · Feb 2026 · superx.so

• 
  KiloClaw▲868

  Hosted OpenClaw. No Mac mini required.

  Dev tools · Feb 2026 · kilo.ai

• 
  Lovon AI Therapy▲801

  Feel closer and have more fun with your partner every day!

  AI · Feb 2026 · lovon.app

• 
  I spent 3 years reverse-engineering a 40 yo stock market sim from 1986▲721

  Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.

  Work · Feb 2026 · wallstreetraider.com