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.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
kev
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b-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%
83.8%
Calibration error
0.054
0.042
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 kev?
bespoke-nimble-9b is from Bespoke Labs and kev from Jared Palmer. bespoke-nimble-9b has open weights and a hosted API; kev has open weights you can download and run. Both answer choice, noul, score, classify and route questions. kev is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or kev?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or kev?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or kev locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull jared-palmer/kev download the weights.
