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.
The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
decision
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-9b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
77.4%
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
—
p95 latency
—
—
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 decision?
bespoke-nimble-9b is from Bespoke Labs and decision from vLLM Semantic Router. bespoke-nimble-9b has open weights and a hosted API; decision has open weights you can download and run. Both answer choice, noul, score, classify and route questions. decision reads up to 16K tokens of state, against 8K tokens for bespoke-nimble-9b.
Which is more accurate, bespoke-nimble-9b or decision?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or decision?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or decision locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull vllm-semantic-router/decision download the weights.
