Dhīr 5B MoE vs EKA-1 vs Olala Mini 7A1B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | |||
|---|---|---|---|
| Task | Multilingual assistant | Multilingual reasoning and coding | Multilingual language generation |
| Published capabilities | Mixture-of-experts assistant supporting English and ten Indian languages for offline deployment. | Trained on about 7.5 trillion tokens across English and all 22 scheduled Indian languages. | Compact mixture-of-experts model combining hybrid attention and Mamba layers. |
| Model size | 5.09B total / 1.79B active | 26.3B parameters | 7B total / 1B active |
| Access | Open weights for on-premises or offline use | Released through the IndiaAI Mission | Downloadable checkpoint for local inference or fine-tuning |
| Sources | Publisher documentation · Additional documentation | Publisher documentation | Model weights · Additional documentation |
| Inputs | Text | Text | Text |
| Context window | 16,384 tokens | — | 32,000 tokens |
| Input price per million tokens | — | — | — |
| Output price per million tokens | — | — | — |
| Weights | Open weights | Weights unconfirmed | Open weights · Apache-2.0 |
| Released | Nov 3, 2026 | Nov 3, 2026 | Nov 19, 2026 |