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.
StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
decider
startlux-decision
Fine-tuned from
qwen/qwen3.5-2b-base
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
26 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 startlux-decision?
decider is from Mapika and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decider answers classify and route. decider is the smaller model, at 1.9B parameters to 4.7B. decider is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, decider or startlux-decision?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or startlux-decision?
decider: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or startlux-decision locally?
Yes, both: systemone pull mapika/decider and systemone pull startlux/startlux-decision download the weights.
