HEAD TO HEAD
Convai Innovations: laya-noulxp-cpu and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya-noulxp-cpu | rizzo-ai-academy/rizzo-flow |
|---|---|---|
| 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. | A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | laya | rizzo-flow |
| Fine-tuned from | convai-innovations/laya | xhtoken/spark-x2.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 64.8% |
| Calibration error | — | 0.112 |
| Valid action rate | — | — |
| Median latency | 116 ms | 195 ms |
| p95 latency | 859 ms | — |
| Evaluation suite | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 |
| Latest version | 0.1.0 | 2026.09 |
| Variants | noulxp | lora, LICENSE |
| Size of latest version | 809.6 MB | 22.0 GB |
| Files | 9 | 17 |
| Downloads | 83 | 2 |
| Stars | 0 | 0 |
| Tags | noulxp, unofficial, onnx, fp32-o23, encoder, modernbert, rlcd | system-one, spark, lora, gguf, llama-cpp, 4b |
| Updated | Nov 21, 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-noulxp-cpu is from Convai Innovations and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. laya-noulxp-cpu is the smaller model, at 421M parameters to 4.0B.
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); laya-noulxp-cpu does not, so there is no comparison to make without your own test.
laya-noulxp-cpu: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, laya-noulxp-cpu answers in about 116 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya-noulxp-cpu and systemone pull rizzo-ai-academy/rizzo-flow download the weights.