ZMIME

Shot Reader 8B vs WeMM-Video-9B

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

Model specifications
SpecificationShot Reader 8BVoyagerWeMM-Video-9BTencent
TaskShot analysisAudio-visual understanding
Published capabilitiesExtracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model.Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode.
Model size8B backbone9B dense language backbone
AccessDownloadable weightsPublic BF16 checkpoint and quantized releases
ResultStructured JSON shot sheetText responses, including descriptions and speech transcripts
SourcesModel weightsModel weights · Additional documentation
InputsText, Images, VideoText, Images, Audio, Video
WeightsOpen weights · Apache-2.0Open weights · Apache-2.0
ReleasedNov 19, 2026Nov 20, 2026