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 | alibi-serikbay/jevk5 | tianyu-codings/nanojev |
|---|---|---|
| Summary | Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF. | 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 | jevk5 | nanojev |
| Fine-tuned from | qwen/qwen3.5-4b | qwen/qwen3-0.6b |
| License | apache-2.0 | mit |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 78.4% | — |
| Calibration error | 0.035 | — |
| Valid action rate | — | — |
| Median latency | 13.2 ms | — |
| p95 latency | — | — |
| Evaluation suite | JevBench public hard tier | — |
| Latest version | 0.3.0 | 2026.09 |
| Variants | SHA256SUMS | tokenizer |
| Size of latest version | 7.9 GB | 2.2 GB |
| Files | 8 | 2 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, distilled, 4b | system-one, games, qwen, research, 0.6b |
| Updated | Sep 26, 2026 | Sep 26, 2026 |