Inkling 2 Mini vs Olala Mini 7A1B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Multimodal reasoning and coding | Multilingual language generation |
| Published capabilities | Reuses its middle layers three times per token. Thinking Machines reports 48.2% on DeepSWE v1.1. | Compact mixture-of-experts model combining hybrid attention and Mamba layers. |
| Model size | 26.4B total / 3.4B active parameters | 7B total / 1B active |
| Access | Downloadable weights and Tinker inference and customization | Downloadable checkpoint for local inference or fine-tuning |
| Operating limits | Native mixed-precision checkpoint occupies approximately 20 GB. | — |
| Sources | Model weights · Additional documentation | Model weights · Additional documentation |
| Inputs | Text, Images | Text |
| Context window | — | 32,000 tokens |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 20, 2026 | Nov 19, 2026 |