HEAD TO HEAD
Contrastive-LM: clm and Convai Innovations: laya-multilingual-noulxp, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | contrastive-lm/clm | convai-innovations/laya-multilingual-noulxp |
|---|---|---|
| Summary | Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking. | 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, rank, classify, route | choice, score, noul, classify, route |
| Architecture | clm | laya |
| Fine-tuned from | qwen/qwen3-8b | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 44.9 ms |
| p95 latency | — | 742 ms |
| Evaluation suite | — | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 |
| Latest version | 2026.09.25 | 0.1.0 |
| Variants | LICENSE | noulxp |
| Size of latest version | 72.1 MB | 648.9 MB |
| Files | 3 | 9 |
| Downloads | 45 | 77 |
| Stars | 0 | 0 |
| Tags | system-one, contrastive, qwen, ranking, 8b | noulxp, unofficial, onnx, fp32-o23, encoder, mmbert, multilingual, rlcd |
| 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.
clm is from Contrastive-LM 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. Only clm answers rank. laya-multilingual-noulxp is the smaller model, at 322M parameters to 8.0B.
Neither publishes an accuracy figure. Test both on your own labelled examples.
clm: Free (open weights). laya-multilingual-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull contrastive-lm/clm and systemone pull convai-innovations/laya-multilingual-noulxp download the weights.