An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
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.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
ajev
laya
Fine-tuned from
google/gemma-4-26b-a4b-it
convai-innovations/laya
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
49 ms
116 ms
p95 latency
—
859 ms
Evaluation suite
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 ajev and laya-noulxp-cpu?
ajev is from Andy Zhang and laya-noulxp-cpu from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya-noulxp-cpu answers classify and route. laya-noulxp-cpu is the smaller model, at 421M parameters to 26B.
Which is more accurate, ajev or laya-noulxp-cpu?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or laya-noulxp-cpu?
ajev: Free (open weights). laya-noulxp-cpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, ajev or laya-noulxp-cpu?
By their publishers’ figures, ajev answers in about 49 ms at the median and laya-noulxp-cpu in about 116 ms — measured on different hardware, so treat it as a rough guide.
Can I run ajev or laya-noulxp-cpu locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull convai-innovations/laya-noulxp-cpu download the weights.
Sequential requests, the maker's own measurement
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
