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.
A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
rizzo-flow
Fine-tuned from
qwen/qwen3.5-9b
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
64.8%
Calibration error
0.054
0.112
Valid action rate
—
—
Median latency
106 ms
195 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 rizzo-flow?
bespoke-nimble-9b is from Bespoke Labs and rizzo-flow from Rizzo AI Academy. bespoke-nimble-9b has open weights and a hosted API; rizzo-flow has open weights you can download and run. Both answer choice, noul, score, classify and route questions. rizzo-flow is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or rizzo-flow?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or rizzo-flow?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or rizzo-flow?
By their publishers’ figures, bespoke-nimble-9b answers in about 106 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run bespoke-nimble-9b or rizzo-flow locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
Bespoke held-out set (324 examples)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
