Shot Reader 8B vs TML-d24-varloop-research
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Shot analysis | Variable-depth reasoning research |
| Published capabilities | Extracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model. | Researchers can vary the number of middle-layer passes with a single checkpoint. |
| Model size | 8B backbone | 26.4B total / 3.4B active parameters |
| Access | Downloadable weights | Downloadable research checkpoint |
| Result | Structured JSON shot sheet | — |
| Operating limits | — | Native mixed-precision checkpoint occupies approximately 20 GB. |
| Sources | Model weights | Model weights · Additional documentation |
| Inputs | Text, Images, Video | Text, Images |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 19, 2026 | Nov 20, 2026 |