Post
4204
MiniCPM-V 4.5 π New MLLM for image, multi-image & video understanding, running even on your phone, released by OpenBMB
openbmb/MiniCPM-V-4_5
β¨ SOTA vision language capability
β¨ 96Γ video token compression > high-FPS & long video reasoning
β¨ Switchable fast vs deep thinking modes
β¨ Strong OCR, document parsing, supports 30+ languages
openbmb/MiniCPM-V-4_5
β¨ SOTA vision language capability
β¨ 96Γ video token compression > high-FPS & long video reasoning
β¨ Switchable fast vs deep thinking modes
β¨ Strong OCR, document parsing, supports 30+ languages