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 | convai-innovations/laya |
|---|---|---|
| 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. | An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | jevk5 | laya |
| Fine-tuned from | qwen/qwen3.5-4b | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| 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 | 39.5 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public hard tier | — |
| Latest version | 0.3.0 | 2026.09.25 |
| Variants | SHA256SUMS | encoder, eval, multilingual, tokenizer, typed-decisions |
| Size of latest version | 7.9 GB | 2.2 GB |
| Files | 8 | 19 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, distilled, 4b | system-one, encoder, modernbert, rlcd, multilingual, 421m |
| Updated | Sep 26, 2026 | Sep 26, 2026 |