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.
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
rizzo-flow
startlux-decision
Fine-tuned from
xhtoken/spark-x2.5-4b
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.8%
88.3%
Calibration error
0.112
—
Valid action rate
—
—
Median latency
195 ms
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 rizzo-flow and startlux-decision?
rizzo-flow is from Rizzo AI Academy and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only rizzo-flow answers classify and route. rizzo-flow is the smaller model, at 4.0B parameters to 4.7B. rizzo-flow is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, rizzo-flow or startlux-decision?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, 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, rizzo-flow or startlux-decision?
rizzo-flow: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, rizzo-flow or startlux-decision?
By their publishers’ figures, startlux-decision answers in about 26 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 rizzo-flow or startlux-decision locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull startlux/startlux-decision download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
JevBench public set (231 items; 204 correct), maker's run
