WeMM-Video-2B vs Olala Mini 7A1B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Audio-visual understanding | Multilingual language generation |
| Published capabilities | Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode. | Compact mixture-of-experts model combining hybrid attention and Mamba layers. |
| Model size | 2B dense language backbone | 7B total / 1B active |
| Access | Public BF16 checkpoint and quantized releases | Downloadable checkpoint for local inference or fine-tuning |
| Result | Text responses, including descriptions and speech transcripts | — |
| Sources | Model weights · Additional documentation | Model weights · Additional documentation |
| Inputs | Text, Images, Audio, Video | Text |
| Context window | — | 32,000 tokens |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 20, 2026 | Nov 19, 2026 |