ZMIME

WeMM-Video-35B-A3B vs Shot Reader 8B

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

Model specifications
SpecificationWeMM-Video-35B-A3BTencentShot Reader 8BVoyager
TaskAudio-visual understandingShot analysis
Published capabilitiesAnswers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode.Extracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model.
Model size35B total / 3B active MoE backbone8B backbone
AccessPublic BF16 checkpoint and quantized releasesDownloadable weights
ResultText responses, including descriptions and speech transcriptsStructured JSON shot sheet
SourcesModel weights · Additional documentationModel weights
InputsText, Images, Audio, VideoText, Images, Video
WeightsOpen weights · Apache-2.0Open weights · Apache-2.0
ReleasedNov 20, 2026Nov 19, 2026