HEAD TO HEAD
Convai Innovations: laya-typed-decisions-noulxp and TokenRhythm: neohorse-jev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya-typed-decisions-noulxp | tokenrhythm/neohorse-jev |
|---|---|---|
| Summary | 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 | — |
| 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 |
| Latest version | 0.1.0 | 2026.09 |
| Variants | noulxp | backbone, SHA256SUMS, assets, dist, package, tokenizer, vision |
| Size of latest version | 809.6 MB | 8.5 GB |
| Files | 9 | 38 |
| Downloads | 91 | 3 |
| Stars | 0 | 0 |
| Tags | noulxp, unofficial, onnx, fp32-o23, encoder, modernbert, rlcd, typed-decisions | system-one, qwen, multimodal, vllm, sglang, 4b |
| Updated | Nov 22, 2026 | Oct 7, 2026 |
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.
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.
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.
laya-typed-decisions-noulxp: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull convai-innovations/laya-typed-decisions-noulxp and systemone pull tokenrhythm/neohorse-jev download the weights.