Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
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.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
rizzo-flow
Fine-tuned from
google/gemma-4-12b-it
xhtoken/spark-x2.5-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
50 ms
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 cygnet and rizzo-flow?
cygnet is from Blockbrain Labs and rizzo-flow from Rizzo AI Academy. 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 12B. cygnet is licensed mit; rizzo-flow, apache-2.0.
Which is more accurate, cygnet or rizzo-flow?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or rizzo-flow?
cygnet: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or rizzo-flow?
By their publishers’ figures, cygnet answers in about 50 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 cygnet or rizzo-flow locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
JevBench public set (231 items), JevBench CLI
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
