ZMIME

Olala Mini 7A1B vs Shot Reader 8B

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

Model specifications
SpecificationOlala Mini 7A1BOVHcloudShot Reader 8BVoyager
TaskMultilingual language generationShot analysis
Published capabilitiesCompact mixture-of-experts model combining hybrid attention and Mamba layers.Extracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model.
Model size7B total / 1B active8B backbone
AccessDownloadable checkpoint for local inference or fine-tuningDownloadable weights
Result—Structured JSON shot sheet
SourcesModel weights · Additional documentationModel weights
InputsTextText, Images, Video
Context window32,000 tokens—
WeightsOpen weights · Apache-2.0Open weights · Apache-2.0
ReleasedNov 19, 2026Nov 19, 2026