MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
No description
UltraRAG 2.0: Less Code, Lower Barrier, Faster Deployment! MCP-based low-code RAG framework, enabling researchers to build complex pipelines to creative innovation.
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
Project Showcase
More >No description
LikeNo description
LikeNo description
LikeNo description
LikeNo description
LikeMiniCPM-o-4_5是开源9B参数多模态模型,视觉能力达OpenCompass 77.6分,超越GPT-4o等,接近Gemini 2.5 Flash。支持中英双语实时语音对话、声音克隆,创新全双工多模态直播,可同时处理音视频流并生成输出,具备强OCR和多语言能力,本地CPU高效推理。【此简介由AI生成】
LikeNo description
LikeNo description
LikeNo description
LikeNo description
Like

