ZMIME

WeMM-Video-9B vs WeMM-Video-35B-A3B

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationWeMM-Video-9BTencentWeMM-Video-35B-A3BTencent
TaskAudio-visual understandingAudio-visual understanding
Published capabilitiesAnswers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode.Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode.
Model size9B dense language backbone35B total / 3B active MoE backbone
AccessPublic BF16 checkpoint and quantized releasesPublic BF16 checkpoint and quantized releases
ResultText responses, including descriptions and speech transcriptsText responses, including descriptions and speech transcripts
SourcesModel weights · Additional documentationModel weights · Additional documentation
InputsText, Images, Audio, VideoText, Images, Audio, Video
WeightsOpen weights · Apache-2.0Open weights · Apache-2.0
ReleasedNov 20, 2026Nov 20, 2026