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.
A Situated World Model for fast judgment in agent loops.
Decides
choice, noul, score, classify, route
choice, route, classify
Architecture
nimble
trio-spark
Fine-tuned from
qwen/qwen3.5-9b
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Bespoke Labs
MachineFi
Input price
—
$0.042/MTok
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)
—
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 trio-spark-v1?
bespoke-nimble-9b is from Bespoke Labs and trio-spark-v1 from MachineFi. bespoke-nimble-9b has open weights and a hosted API; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only bespoke-nimble-9b answers noul and score. bespoke-nimble-9b reads up to 8K tokens of state, against 1K tokens for trio-spark-v1. bespoke-nimble-9b is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, bespoke-nimble-9b or trio-spark-v1?
Only bespoke-nimble-9b publishes an accuracy figure (90.1% on Bespoke held-out set (324 examples)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, bespoke-nimble-9b or trio-spark-v1?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or trio-spark-v1 locally?
bespoke-nimble-9b yes — systemone pull bespoke-labs/bespoke-nimble-9b downloads its weights. The other is only served as a hosted API.
