Aion 1.0 Instruct 2.3B vs WeMM-Video-35B-A3B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | On-device language generation | Audio-visual understanding |
| Published capabilities | Windows-oriented instruction model for local text generation, including document and email tasks. | Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode. |
| Model size | 2.3B parameters | 35B total / 3B active MoE backbone |
| Access | Downloadable checkpoint | Public BF16 checkpoint and quantized releases |
| Result | — | Text responses, including descriptions and speech transcripts |
| Operating limits | 32K-token context window | — |
| Sources | Model weights | Model weights · Additional documentation |
| Inputs | Text | Text, Images, Audio, Video |
| Weights | Open weights · MIT | Open weights · Apache-2.0 |
| Released | Nov 18, 2026 | Nov 20, 2026 |