An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
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, classify, route
choice, score, noul, classify, route
Architecture
laya
rizzo-flow
Fine-tuned from
answerdotai/modernbert-large
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
39.5 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 laya and rizzo-flow?
laya is from Convai Innovations and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. laya is the smaller model, at 421M parameters to 4.0B.
Which is more accurate, laya or rizzo-flow?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); laya does not, so there is no comparison to make without your own test.
Which is cheaper, laya or rizzo-flow?
laya: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya or rizzo-flow?
By their publishers’ figures, laya answers in about 39.5 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 laya or rizzo-flow locally?
Yes, both: systemone pull convai-innovations/laya and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
—
Evaluation suite
—
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
