WeMM-Video-4B
AvailableDense 4B model in Tencent's WeMM-Video family of Chinese-English bilingual omni-modal models for joint audio-visual understanding and reasoning. It takes text, image, audio and video input (including video with its original soundtrack) and outputs text, with instruct and thinking modes. Vision and Whisper-style audio encoders feed a Qwen3.5-architecture language backbone. Pretrained on about 1.2T multimodal tokens, then post-trained with multi-teacher OPD, anti-repetition MrDPO and specialist RL. Technical report on arXiv Nov 19 2026; Apache 2.0 weights uploaded to Hugging Face Nov 20 2026 (about 5.6B parameters in the checkpoint, including encoders), with FP8, AWQ, GGUF and NVFP4 builds. Context length not stated on the model card.
Specifications
- License
- Open source · Apache-2.0
- Weights
- Downloadable
- Architecture
- Dense
- Parameters
- 4B
- Context window
- — tokens
- Max output
- —
- Knowledge cutoff
- —
- Price (in / out, $/M)
- —
- Modalities
- TextVisionAudioVideo
Benchmarks
No benchmark scores recorded yet. Spotted some? Submit a correction.
Vendor-reported figures are claims until independently verified. See methodology.