HEAD TO HEAD
Jared Palmer: kev and Convai Innovations: laya-multilingual-noulxp, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | jared-palmer/kev | convai-innovations/laya-multilingual-noulxp |
|---|---|---|
| Summary | An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint. | Unofficial NoulXP package of Convai Innovations' Laya multilingual (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | kev | laya |
| Fine-tuned from | qwen/qwen3.5-4b-base | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 83.8% | — |
| Calibration error | 0.042 | — |
| Valid action rate | — | — |
| Median latency | — | 44.9 ms |
| p95 latency | — | 742 ms |
| Evaluation suite | transfer-v4 (locked, out of domain) | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 |
| Latest version | 2026.09 | 0.1.0 |
| Variants | — | noulxp |
| Size of latest version | 152.2 MB | 648.9 MB |
| Files | 11 | 9 |
| Downloads | 1 | 77 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, pointer-head, 4b | noulxp, unofficial, onnx, fp32-o23, encoder, mmbert, multilingual, rlcd |
| Updated | Oct 7, 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.
kev is from Jared Palmer and laya-multilingual-noulxp from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. kev reads up to 8K tokens of state, against 1K tokens for laya-multilingual-noulxp. laya-multilingual-noulxp is the smaller model, at 322M parameters to 4.0B.
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); laya-multilingual-noulxp does not, so there is no comparison to make without your own test.
kev: Free (open weights). laya-multilingual-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull jared-palmer/kev and systemone pull convai-innovations/laya-multilingual-noulxp download the weights.