A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
anyjev
startlux-decision
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
88.3%
Calibration error
0.034
—
Valid action rate
—
—
Median latency
—
26 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 anyjev and startlux-decision?
anyjev is from Nokia and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only anyjev answers classify and route. startlux-decision is the smaller model, at 4.7B parameters to 8.0B. anyjev is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, anyjev or startlux-decision?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or startlux-decision?
anyjev: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or startlux-decision locally?
Yes, both: systemone pull nokia/anyjev and systemone pull startlux/startlux-decision download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
JevBench public set (231 items; 204 correct), maker's run
