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 | jared-palmer/kev | aac6fef/laya-mlx |
|---|---|---|
| Summary | An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint. | Native MLX FP16 conversion of Laya for Apple silicon. The same ModernBERT-large encoder, decision transformer and heads, running in MLX with no PyTorch; the checkpoint Laya Studio fine-tunes from. |
| Decides | choice, score, noul, classify, route | choice, score, noul |
| Architecture | kev | laya |
| Fine-tuned from | qwen/qwen3.5-4b-base | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 83.8% | — |
| Calibration error | 0.042 | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | transfer-v4 (locked, out of domain) | — |
| Latest version | 2026.09 | 2026.09 |
| Variants | — | encoder, tokenizer, LICENSE, NOTICE |
| Size of latest version | 152.2 MB | 807.0 MB |
| Files | 11 | 10 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, pointer-head, 4b | system-one, mlx, apple-silicon, modernbert, conversion, 421m |
| Updated | Sep 26, 2026 | Sep 26, 2026 |