HEAD TO HEAD
Supersonic Labs: julia-1 and Convai Innovations: laya-typed-decisions-noulxp, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | supersonic-labs/julia-1 | convai-innovations/laya-typed-decisions-noulxp |
|---|---|---|
| Summary | A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU. | Unofficial NoulXP package of Convai Innovations' Laya typed-decisions (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 | julia | laya |
| Fine-tuned from | jhu-clsp/mmbert-small | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.2% | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 126 ms |
| p95 latency | — | 2185 ms |
| Evaluation suite | typed-decisions test set (400 cases, 2,000 questions) | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 |
| Latest version | 1.0.0 | 0.1.0 |
| Variants | julia, tests, scripts, metrics, encoder, tokenizer | noulxp |
| Size of latest version | 583.4 MB | 809.6 MB |
| Files | 40 | 9 |
| Downloads | 853 | 86 |
| Stars | 1 | 0 |
| Tags | system-one, encoder, mmbert, multilingual, cpu, 144m | noulxp, unofficial, onnx, fp32-o23, encoder, modernbert, rlcd, typed-decisions |
| Updated | Nov 21, 2026 | Nov 21, 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.
julia-1 is from Supersonic Labs and laya-typed-decisions-noulxp from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 reads up to 8K tokens of state, against 1K tokens for laya-typed-decisions-noulxp. julia-1 is the smaller model, at 144M parameters to 421M.
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); laya-typed-decisions-noulxp does not, so there is no comparison to make without your own test.
julia-1: Free (open weights). laya-typed-decisions-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull convai-innovations/laya-typed-decisions-noulxp download the weights.