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
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bespoke-nimble-9b and laya-mlx?
bespoke-nimble-9b is from Bespoke Labs and laya-mlx from aac6fef. bespoke-nimble-9b has open weights and a hosted API; laya-mlx has open weights you can download and run. Both answer choice, noul and score questions. Only bespoke-nimble-9b answers classify and route. bespoke-nimble-9b reads up to 8K tokens of state, against 512 tokens for laya-mlx. laya-mlx is the smaller model, at 421M parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or laya-mlx?
Only bespoke-nimble-9b publishes an accuracy figure (90.1% on Bespoke held-out set (324 examples)); laya-mlx does not, so there is no comparison to make without your own test.
Which is cheaper, bespoke-nimble-9b or laya-mlx?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. laya-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or laya-mlx locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull aac6fef/laya-mlx download the weights.
