HEAD TO HEAD
Convai Innovations: laya-noulxp-cpu and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya-noulxp-cpu | sagea/mira |
|---|---|---|
| Summary | 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. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | laya | mira |
| Fine-tuned from | convai-innovations/laya | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 61.3% |
| Calibration error | — | 0.083 |
| Valid action rate | — | 100.0% |
| Median latency | 116 ms | 30 ms |
| p95 latency | 859 ms | 43 ms |
| Evaluation suite | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 | s1-decision-bench |
| Latest version | 0.1.0 | 0.1.5 |
| Variants | noulxp | — |
| Size of latest version | 809.6 MB | 568.8 MB |
| Files | 9 | 12 |
| Downloads | 83 | 222 |
| Stars | 0 | 1 |
| Tags | noulxp, unofficial, onnx, fp32-o23, encoder, modernbert, rlcd | routing, nepali, nepal, calibration, cpu |
| Updated | Nov 21, 2026 | Nov 22, 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-noulxp-cpu is from Convai Innovations and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Only mira publishes an accuracy figure (61.3% on s1-decision-bench); laya-noulxp-cpu does not, so there is no comparison to make without your own test.
laya-noulxp-cpu: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, mira answers in about 30 ms at the median and laya-noulxp-cpu in about 116 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya-noulxp-cpu and systemone pull sagea/mira download the weights.