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.
Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
simple-jev
Fine-tuned from
qwen/qwen3.5-9b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights + hosted API
Hosted by
Bespoke Labs
Featherless AI
Input price
—
—
Decision accuracy
90.1%
—
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 simple-jev?
bespoke-nimble-9b is from Bespoke Labs and simple-jev from Featherless AI. Both have open weights and a hosted API. Both answer choice, noul, score, classify and route questions.
Which is more accurate, bespoke-nimble-9b or simple-jev?
Only bespoke-nimble-9b publishes an accuracy figure (90.1% on Bespoke held-out set (324 examples)); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, bespoke-nimble-9b or simple-jev?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or simple-jev locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull featherless-ai/simple-jev download the weights.
