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.
Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
jevk5
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
78.4%
Calibration error
0.054
0.035
Valid action rate
—
—
Median latency
106 ms
13.2 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 jevk5?
bespoke-nimble-9b is from Bespoke Labs and jevk5 from Alibi Serikbay. bespoke-nimble-9b has open weights and a hosted API; jevk5 has open weights you can download and run. Both answer choice, noul, score, classify and route questions. jevk5 is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or jevk5?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), jevk5 78.4% on JevBench public hard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or jevk5?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. jevk5: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or jevk5?
By their publishers’ figures, jevk5 answers in about 13.2 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 jevk5 locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull alibi-serikbay/jevk5 download the weights.
