A compact, no-frills text model that handles basic language tasks with modest capability. At 1.3 billion parameters, it operates within tight constraints — coherent for short, simple completions but struggles with complex reasoning or nuanced instruction following. Think of it as a lightweight workhorse suited for experimentation and research rather than production-grade tasks.
| Benchmark | Score | Type | Recorded |
|---|---|---|---|
| IFEval | 23.8 | accuracy | 4d ago |