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 most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
decider
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-2b-base
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
80.2%
Calibration error
0.054
0.038
Valid action rate
—
—
Median latency
106 ms
3.2 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 decider?
bespoke-nimble-9b is from Bespoke Labs and decider from Mapika. bespoke-nimble-9b has open weights and a hosted API; decider has open weights you can download and run. Both answer choice, noul, score, classify and route questions. decider is the smaller model, at 2.0B parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or decider?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), decider 80.2% on Decider 67-task regression set — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or decider?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or decider?
By their publishers’ figures, decider answers in about 3.2 ms at the median and bespoke-nimble-9b in about 106 ms — measured on different hardware, so treat it as a rough guide.
Can I run bespoke-nimble-9b or decider locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull mapika/decider download the weights.
