Aurora2-400M-A20M vs Olala Mini 7A1B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Base language modeling | Multilingual language generation |
| Published capabilities | English base model pretrained on 100 billion tokens with one shared expert and 32 routed experts per layer. | Compact mixture-of-experts model combining hybrid attention and Mamba layers. |
| Model size | 400M total / approximately 19M active parameters | 7B total / 1B active |
| Access | Public Transformers checkpoint for completion and adaptation | Downloadable checkpoint for local inference or fine-tuning |
| Sources | Model weights | Model weights · Additional documentation |
| Inputs | Text | Text |
| Context window | — | 32,000 tokens |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 18, 2026 | Nov 19, 2026 |