Loading comparison…
COMPARE
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | mapika/decider | tianyu-codings/nanojev |
|---|---|---|
| Summary | The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot. | A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline. |
| Decides | choice, score, noul, classify, route | choice, noul, score |
| Architecture | decider | nanojev |
| Fine-tuned from | qwen/qwen3.5-2b-base | qwen/qwen3-0.6b |
| License | apache-2.0 | mit |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 80.2% | — |
| Calibration error | 0.038 | — |
| Valid action rate | — | — |
| Median latency | 3.2 ms | — |
| p95 latency | — | — |
| Evaluation suite | Decider 67-task regression set | — |
| Latest version | 2026.09 | 2026.09 |
| Variants | — | tokenizer |
| Size of latest version | 3.5 GB | 2.2 GB |
| Files | 4 | 2 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, rl, calibrated, 2b | system-one, games, qwen, research, 0.6b |
| Updated | Sep 26, 2026 | Sep 26, 2026 |