Olala Mini 7A1B vs Shot Reader 8B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Multilingual language generation | Shot analysis |
| Published capabilities | Compact 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 size | 7B total / 1B active | 8B backbone |
| Access | Downloadable checkpoint for local inference or fine-tuning | Downloadable weights |
| Result | — | Structured JSON shot sheet |
| Sources | Model weights · Additional documentation | Model weights |
| Inputs | Text | Text, Images, Video |
| Context window | 32,000 tokens | — |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 19, 2026 | Nov 19, 2026 |