ZMIME

TML-d24-varloop-research vs Shot Reader 8B

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

Model specifications
SpecificationTML-d24-varloop-researchThinking MachinesShot Reader 8BVoyager
TaskVariable-depth reasoning researchShot analysis
Published capabilitiesResearchers can vary the number of middle-layer passes with a single checkpoint.Extracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model.
Model size26.4B total / 3.4B active parameters8B backbone
AccessDownloadable research checkpointDownloadable weights
Result—Structured JSON shot sheet
Operating limitsNative mixed-precision checkpoint occupies approximately 20 GB.—
SourcesModel weights · Additional documentationModel weights
InputsText, ImagesText, Images, Video
WeightsOpen weights · Apache-2.0Open weights · Apache-2.0
ReleasedNov 20, 2026Nov 19, 2026