openbmb/MiniCPM-V-4.6

MiniCPM-V 4.6 (1.3B) — pocket-sized multimodal LLM for ultra-efficient single-image, multi-image, and video understanding, built on SigLIP2-400M + a Qwen3.5-0.8B hybrid-attention backbone

~1.5× token throughput vs Qwen3.5-0.8B with mixed 4×/16× visual token compression

View on HuggingFaceView on ModelScope