Unofficial NoulXP package of Convai Innovations' Laya typed-decisions (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
laya
neohorse
Fine-tuned from
convai-innovations/laya
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
126 ms
—
p95 latency
2185 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-typed-decisions-noulxp and neohorse-jev?
laya-typed-decisions-noulxp is from Convai Innovations and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. laya-typed-decisions-noulxp is the smaller model, at 421M parameters to 4.0B.
Which is more accurate, laya-typed-decisions-noulxp or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); laya-typed-decisions-noulxp does not, so there is no comparison to make without your own test.
Which is cheaper, laya-typed-decisions-noulxp or neohorse-jev?
laya-typed-decisions-noulxp: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya-typed-decisions-noulxp or neohorse-jev locally?
Yes, both: systemone pull convai-innovations/laya-typed-decisions-noulxp and systemone pull tokenrhythm/neohorse-jev 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), vLLM, maker's run
