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.
Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
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 laya-noulxp-cpu?
decider is from Mapika and laya-noulxp-cpu from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider reads up to 32K tokens of state, against 512 tokens for laya-noulxp-cpu. laya-noulxp-cpu is the smaller model, at 421M parameters to 1.9B.
Which is more accurate, decider or laya-noulxp-cpu?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); laya-noulxp-cpu does not, so there is no comparison to make without your own test.
Which is cheaper, decider or laya-noulxp-cpu?
decider: Free (open weights). laya-noulxp-cpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or laya-noulxp-cpu locally?
Yes, both: systemone pull mapika/decider and systemone pull convai-innovations/laya-noulxp-cpu download the weights.
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
