Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/MiniCPM-o
Library/MiniCPM-oForked

OpenBMB/MiniCPM-V

MiniCPM-o

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

View on GitHub↗Upstream OpenBMB/MiniCPM-V↗

Builder

OpenBMB

OpenBMB

OpenBMB • individual

Stars

25,411

Using upstream star count

Forks

1,993

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jan 29, 2024

Project creation date

README Summary

<img src="./assets/minicpm_v_and_minicpm_o_title.png" width="500em" ></img>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Cross-modal ReasoningLive Multimodal InteractionMobile AI DeploymentModel Compression and OptimizationMultimodal Large Language ModelsReal-time Streaming AISpeech ProcessingVision-Language Understanding

Tags

Cross-modal ReasoningLive Multimodal InteractionMobile AI DeploymentModel Compression and OptimizationMultimodal Large Language ModelsReal-time Streaming AISpeech ProcessingVision-Language UnderstandingAI SafetyAnthropic / ClaudeBenchmarkingC++Cheat SheetClaudeComfyUIDPODeepSeekDockerDocument ProcessingEvalsForkedGPTGPU / CUDAGoogle AIHuggingFaceHumanEvalImage GenerationKV CacheLLM ServingLarge Language ModelsLlamaLoRA / PEFTMMLUMobileMultimodal AINode.jsNumPyOllamaOpen SourceOpenAIPhiPlanning / CoTPrompt EngineeringPyTorchPythonQuantizationQwenRLHFReal-Time / StreamingReinforcement LearningResearch / PapersSGLangSecuritySpeech to TextStatisticsText to SpeechTransformersVideo Generationllama.cppvLLM

Taxonomy

AI Trends

On-device AIMultimodal ReasoningSmall Language ModelsEdge AIReal-time AI

category

Foundation ModelsAI AgentsRAG & RetrievalModel TrainingEvals & BenchmarkingInference & ServingGenerative MediaMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesSecurity & SafetyData Science & Analytics

Deployment Context

Edge/MobileSelf-hosted

Industries

Mobile App DevelopmentConsumer ElectronicsTelecommunicationsDeveloper Tools

Modalities

TextImageAudioVideoMultimodal

Skill Areas

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

tag

AI SafetyAnthropic / ClaudeBenchmarkingC++Cheat SheetClaudeComfyUIDPODeepSeekDockerDocument ProcessingEvalsForkedGPTGPU / CUDAGoogle AIHuggingFaceHumanEvalImage GenerationKV CacheLLM ServingLarge Language ModelsLlamaLoRA / PEFTMMLUMobileMultimodal AINode.jsNumPyOllamaOpen SourceOpenAIPhiPlanning / CoTPrompt EngineeringPyTorchPythonQuantizationQwenRLHFReal-Time / StreamingReinforcement LearningResearch / PapersSGLangSecuritySpeech to TextStatisticsText to SpeechTransformersVideo Generationllama.cppvLLM

Use Cases

Real-time Visual Question AnsweringLive Video Stream AnalysisVoice-Visual Interactive AssistantsMobile Multimodal Chat ApplicationsFull-Duplex Conversational AIOn-device Image Understanding

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

4

Update links in README_zh.md for MiniCPM

Boke Syo • Mar 7, 2026

1d7e7b9

Update MiniCPM-o demo link in README

Boke Syo • Mar 7, 2026

c0ec8ee

Fix formatting and update links in README.md

Boke Syo • Mar 6, 2026

2ce8822

Quality

research
Quality
medium
Maturity
research

Categories

Foundation ModelsPrimaryAI AgentsRAG & RetrievalModel TrainingEvals & BenchmarkingInference & ServingGenerative MediaSafety & AlignmentCoding & Dev ToolsData Science & AnalyticsMultimodal AIEdge & Mobile AISearch & KnowledgeOther AI / MLMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesSecurity & Safety

PM Skills

Cost & EfficiencySafety & AlignmentUser ExperienceScale & ReliabilityData & EvaluationProduct DiscoveryAI-Native Architecture

Languages

Python100.0%

Timeline

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

Similar Repos

pgvector cosine similarity · $0

Loading…