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 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, score, noul, classify, route
choice, score, noul, rank, extract
Architecture
rizzo-flow
solvi
Fine-tuned from
xhtoken/spark-x2.5-4b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.8%
59.4%
Calibration error
0.112
0.210
Valid action rate
—
—
Median latency
195 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 solvi?
rizzo-flow is from Rizzo AI Academy and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only rizzo-flow answers classify and route. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 4.0B.
Which is more accurate, rizzo-flow or solvi?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, rizzo-flow or solvi?
rizzo-flow: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or solvi locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
