Library/MiniCPM-o
Library/MiniCPM-oForked

OpenBMB/MiniCPM-o

MiniCPM-o

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

Builder

OpenBMB

OpenBMB

OpenBMB • individual

Stars

24,271

Using upstream star count

Forks

1,888

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jan 29, 2024

Project creation date

README Summary

MiniCPM-o is a multimodal large language model that achieves Gemini 2.5 Flash level performance for vision, speech, and real-time multimodal interactions. The model is optimized to run efficiently on mobile devices while supporting full-duplex multimodal live streaming capabilities. It represents a significant advancement in bringing high-quality multimodal AI to edge devices with minimal computational resources.

AI Dev Skills

Unmapped

Multimodal Large Language ModelsVision-Language UnderstandingSpeech ProcessingReal-time Streaming AIModel Compression and OptimizationMobile AI DeploymentCross-modal ReasoningLive Multimodal Interaction

Tags

Multimodal Large Language ModelsVision-Language UnderstandingSpeech ProcessingReal-time Streaming AIModel Compression and OptimizationMobile AI DeploymentCross-modal ReasoningLive Multimodal InteractionOn-device Image UnderstandingMobile App DevelopmentVoice-Visual Interactive AssistantsEdge/MobileMultimodal ReasoningEdge AILive Video Stream AnalysisDeveloper ToolsSelf-hostedVideoTelecommunicationsConsumer ElectronicsReal-time Visual Question AnsweringMultimodalMobile Multimodal Chat ApplicationsTextReal-time AIFull-Duplex Conversational AIAudioOn-device AIImageSmall Language ModelsPython

Taxonomy

Recent Activity

Updated 1 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

research
Quality
medium
Maturity
research

Categories

Dev Tools & AutomationPrimaryNLP & TextCoding & Dev ToolsMultimodal AIEdge & Mobile AISearch & KnowledgeOther AI / MLInference & ServingFoundation ModelsGenerative MediaComputer VisionRobotics

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Jan 29, 2024
Forked
Mar 22, 2026
Your last push
1 months ago
Upstream last push
12 days ago
Tracked since
Mar 7, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…