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 Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
rizzo-flow
trio-spark
Fine-tuned from
xhtoken/spark-x2.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
64.8%
—
Calibration error
0.112
—
Valid action rate
—
—
Median latency
195 ms
—
p95 latency
—
—
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
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 trio-spark-v1?
rizzo-flow is from Rizzo AI Academy and trio-spark-v1 from MachineFi. rizzo-flow has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only rizzo-flow answers score and noul. rizzo-flow is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, rizzo-flow or trio-spark-v1?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, rizzo-flow or trio-spark-v1?
rizzo-flow: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or trio-spark-v1 locally?
rizzo-flow yes — systemone pull rizzo-ai-academy/rizzo-flow downloads its weights. The other is only served as a hosted API.
