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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
rizzo-flow
scorer
Fine-tuned from
xhtoken/spark-x2.5-4b
qwen/qwen3.5-4b-base
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.8%
70.7%
Calibration error
0.112
0.044
Valid action rate
—
—
Median latency
195 ms
112 ms
p95 latency
—
—
Evaluation suite
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 system-one-qwen3-5-4b-scorer?
rizzo-flow is from Rizzo AI Academy and system-one-qwen3-5-4b-scorer from pngwn. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only rizzo-flow answers route. rizzo-flow is licensed apache-2.0; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, rizzo-flow or system-one-qwen3-5-4b-scorer?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, system-one-qwen3-5-4b-scorer 70.7% on author-reported — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, rizzo-flow or system-one-qwen3-5-4b-scorer?
rizzo-flow: Free (open weights). system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, rizzo-flow or system-one-qwen3-5-4b-scorer?
By their publishers’ figures, system-one-qwen3-5-4b-scorer answers in about 112 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 system-one-qwen3-5-4b-scorer locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull pngwn/system-one-qwen3-5-4b-scorer download the weights.
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
