Loading comparison…
HEAD TO HEAD
Bofeng Huang: docto-decision and Convai Innovations: laya-noulxp-gpu, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | bofeng-huang/docto-decision | convai-innovations/laya-noulxp-gpu |
|---|---|---|
| Summary | French medical decision models by Bofeng Huang: pass a patient message or clinical note, a question and candidate answers, and get one probability per answer from a single forward pass. Choice, score and noul. A research model, not a medical device. | Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp16: checked against the model's own answers, none changed. Not made by Convai Innovations. |
| Decides | choice, score, noul | choice, score, noul, classify, route |
| Architecture | docto-decision | laya |
| Fine-tuned from | qwen/qwen3.5-4b | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 88.9% | — |
| Calibration error | 0.079 | — |
| Valid action rate | — | — |
| Median latency | 47 ms | — |
| p95 latency | — | — |
| Evaluation suite | Docto Decision Bench fr v0.1 (12 tasks, mostly silver labels; the maker's own benchmark) | — |
| Latest version | 0.1.0 | 0.1.0 |
| Variants | LICENSE, adapters | noulxp |
| Size of latest version | 8.8 GB | 958.6 MB |
| Files | 13 | 9 |
| Downloads | 0 | 36 |
| Stars | 0 | 0 |
| Tags | system-one, french, medical, qwen, lora, 4.66b | noulxp, unofficial, onnx, fp16, 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.
docto-decision is from Bofeng Huang and laya-noulxp-gpu from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya-noulxp-gpu answers classify and route. laya-noulxp-gpu is the smaller model, at 421M parameters to 4.7B.
Only docto-decision publishes an accuracy figure (88.9% on Docto Decision Bench fr v0.1 (12 tasks, mostly silver labels; the maker's own benchmark)); laya-noulxp-gpu does not, so there is no comparison to make without your own test.
docto-decision: Free (open weights). laya-noulxp-gpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull bofeng-huang/docto-decision and systemone pull convai-innovations/laya-noulxp-gpu download the weights.