WeMM-Video-2B vs Aion 1.0 Instruct 2.3B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Audio-visual understanding | On-device language generation |
| Published capabilities | Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode. | Windows-oriented instruction model for local text generation, including document and email tasks. |
| Model size | 2B dense language backbone | 2.3B parameters |
| Access | Public BF16 checkpoint and quantized releases | Downloadable checkpoint |
| Result | Text responses, including descriptions and speech transcripts | — |
| Operating limits | — | 32K-token context window |
| Sources | Model weights · Additional documentation | Model weights |
| Inputs | Text, Images, Audio, Video | Text |
| Weights | Open weights · Apache-2.0 | Open weights · MIT |
| Released | Nov 20, 2026 | Nov 18, 2026 |