ZMIME

Shot Reader 8B vs Hy4 Base

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

Model specifications
SpecificationShot Reader 8BVoyagerHy4 BaseTencent
TaskShot analysisMultimodal pretraining
Published capabilitiesExtracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model.Pretrained checkpoint for continued training and adaptation. Tencent’s flagship Hy4 uses a 78-layer language backbone with a separate vision encoder.
Model size8B backbone770B total / 49B active per token in the language backbone
AccessDownloadable weightsDownloadable under the Tencent Hy License
ResultStructured JSON shot sheet—
SourcesModel weightsModel weights
InputsText, Images, VideoText, Images, Video
WeightsOpen weights · Apache-2.0Open weights · Tencent Hy License
ReleasedNov 19, 2026Nov 20, 2026