Loading comparison…
HEAD TO HEAD
Ruoxi Qiu: canopy-jev and Convai Innovations: laya-noulxp-cpu, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | convai-innovations/laya-noulxp-cpu |
|---|---|---|
| Summary | Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens. | 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, noul, score | choice, score, noul, classify, route |
| Architecture | canopy-jev | laya |
| Fine-tuned from | qwen/qwen3.8-27b | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.4% | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 116 ms |
| p95 latency | — | 859 ms |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 |
| Latest version | 0.1.0 | 0.1.0 |
| Variants | LICENSE, NOTICE, artifacts, licenses | noulxp |
| Size of latest version | 24.1 MB | 809.6 MB |
| Files | 11 | 9 |
| Downloads | 0 | 32 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | noulxp, unofficial, onnx, fp32-o23, encoder, modernbert, rlcd |
| Updated | Oct 7, 2026 | Oct 24, 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.
canopy-jev is from Ruoxi Qiu and laya-noulxp-cpu from Convai Innovations. Both have open weights you can download and run. Both answer choice, noul and score questions. Only laya-noulxp-cpu answers classify and route. laya-noulxp-cpu is the smaller model, at 421M parameters to 27B.
Only canopy-jev publishes an accuracy figure (87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer); laya-noulxp-cpu does not, so there is no comparison to make without your own test.
canopy-jev: Free (open weights). laya-noulxp-cpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull convai-innovations/laya-noulxp-cpu download the weights.