Back to models
OpenBMB
MiniCPM-V 4.6
Open Weightsapache-2.0Released May 2026
Ultra-efficient multimodal language model from OpenBMB built on SigLIP2-400M and Qwen3.5-0.8B (~1B parameters). Supports single-image, multi-image, and video understanding with mixed 4x/16x visual token compression. Designed for edge deployment on iOS, Android, and HarmonyOS.
Capabilities
chatcompletionvision
Modalities
textimagevideo
Context Window
256K tokens
Providers
0
No provider data available yet.
Provider mappings will appear here once the API is connected.