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 | bespoke-labs/bespoke-nimble-9b | aac6fef/laya-mlx |
|---|---|---|
| Summary | An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it. | 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, noul, score, classify, route | choice, score, noul |
| Architecture | nimble | laya |
| Fine-tuned from | qwen/qwen3.5-9b | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights + hosted API | Open weights |
| Hosted by | Bespoke Labs | — |
| Input price | — | — |
| Decision accuracy | 90.1% | — |
| Calibration error | 0.054 | — |
| Valid action rate | — | — |
| Median latency | 106 ms | — |
| p95 latency | — | — |
| Evaluation suite | Bespoke held-out set (324 examples) | — |
| Latest version | 2026.09 | 2026.09 |
| Variants | SHA256SUMS | encoder, tokenizer, LICENSE, NOTICE |
| Size of latest version | 184.3 MB | 807.0 MB |
| Files | 10 | 10 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, curated-data, 9b | system-one, mlx, apple-silicon, modernbert, conversion, 421m |
| Updated | Sep 26, 2026 | Sep 26, 2026 |