HEAD TO HEAD
Andy Zhang: ajev and Convai Innovations: laya, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | convai-innovations/laya |
|---|---|---|
| Summary | An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass. | An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. |
| Decides | choice, score, noul | choice, score, noul, classify, route |
| Architecture | ajev | laya |
| Fine-tuned from | google/gemma-4-26b-a4b-it | answerdotai/modernbert-large |
| 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 | 49 ms | 39.5 ms |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | — |
| Latest version | 2026.09 | 2026.09.25 |
| Variants | — | multilingual, tokenizer, eval, typed-decisions, encoder |
| Size of latest version | 141.9 MB | 2.2 GB |
| Files | 3 | 19 |
| Downloads | 0 | 431 |
| Stars | 0 | 0 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, encoder, modernbert, rlcd, multilingual, 421m |
| 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.
ajev is from Andy Zhang and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. laya is the smaller model, at 421M parameters to 26B.
Neither publishes an accuracy figure. Test both on your own labelled examples.
ajev: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, laya answers in about 39.5 ms at the median and ajev in about 49 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull andy-zhang/ajev and systemone pull convai-innovations/laya download the weights.