A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
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
decider
rizzo-flow
Fine-tuned from
qwen/qwen3.5-2b-base
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
64.8%
Calibration error
—
0.112
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 decider and rizzo-flow?
decider is from Mapika 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. decider is the smaller model, at 1.9B parameters to 4.0B.
Which is more accurate, decider or rizzo-flow?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), 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, decider or rizzo-flow?
decider: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or rizzo-flow locally?
Yes, both: systemone pull mapika/decider and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
