Unofficial NoulXP package of Convai Innovations' Laya multilingual (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
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
laya
startlux-decision
Fine-tuned from
convai-innovations/laya
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
44.9 ms
26 ms
p95 latency
742 ms
—
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-multilingual-noulxp and startlux-decision?
laya-multilingual-noulxp is from Convai Innovations and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya-multilingual-noulxp answers classify and route. laya-multilingual-noulxp is the smaller model, at 322M parameters to 4.7B. laya-multilingual-noulxp is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, laya-multilingual-noulxp or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); laya-multilingual-noulxp does not, so there is no comparison to make without your own test.
Which is cheaper, laya-multilingual-noulxp or startlux-decision?
laya-multilingual-noulxp: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya-multilingual-noulxp or startlux-decision?
By their publishers’ figures, startlux-decision answers in about 26 ms at the median and laya-multilingual-noulxp in about 44.9 ms — measured on different hardware, so treat it as a rough guide.
Can I run laya-multilingual-noulxp or startlux-decision locally?
Yes, both: systemone pull convai-innovations/laya-multilingual-noulxp and systemone pull startlux/startlux-decision download the weights.
Evaluation suite
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
JevBench public set (231 items; 204 correct), maker's run
