Nanjing University's MCG team (S-Lab) recently open-sourced VideoChat3 — a 4B-parameter fully open video MLLM that topped the Hugging Face trending top 3, with "one model handling all video understanding" as the main feature: fine-grained motion perception, hour-level long video, temporal grounding, and streaming response all in one. Two core innovations: I3D-ViT: 16× compression of spatiotemporal tokens, significantly reducing visual encoding cost. Adaptive Frame Resolution for Streaming: on-demand frame resolution upscaling, avoiding per-frame high-resolution computation. The team simultaneously open-sourced three datasets — Academic2M (general), LV116K (long video), OL617K (streaming) — covering the entire training chain. VideoChat3 delivers model weights, data, and synthesis pipeline in one go — this is quite rare in the video MLLM circle, where most strong models only release weights, not data. Experiments show VideoChat3 outperforms open-source opponents with larger parameter scales on all three categories: general, long video, and streaming. Unified architecture + adaptive frame rate + compact token representation, packing four capabilities into 4B — that's the key step for video MLLM to move toward engineering.