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.
A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
rizzo-flow
wald
Fine-tuned from
xhtoken/spark-x2.5-4b
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.8%
88.3%
Calibration error
0.112
0.045
Valid action rate
—
—
Median latency
195 ms
33 ms
p95 latency
—
168 ms
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 wald?
rizzo-flow is from Rizzo AI Academy and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. rizzo-flow is the smaller model, at 4.0B parameters to 4.2B.
Which is more accurate, rizzo-flow or wald?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, rizzo-flow or wald?
rizzo-flow: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, rizzo-flow or wald?
By their publishers’ figures, wald answers in about 33 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 wald locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull org2ai/wald download the weights.
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
Latest version
2026.09
1.2.0
Variants
lora, LICENSE
Dockerfile, LICENSE, NOTICE, model-files, reference, server
