HEAD TO HEAD
Convai Innovations: laya and FrontiersMind: lumma-fev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya | frontiersmind/lumma-fev |
|---|---|---|
| Summary | 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. | FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated. |
| Decides | choice, score, noul, classify, route | choice, score, noul |
| Architecture | laya | lumma-fev |
| Fine-tuned from | answerdotai/modernbert-large | frontiersmind/lumma-0.6b-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 64.0% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 39.5 ms | 45.8 ms |
| p95 latency | — | — |
| Evaluation suite | — | typed-decisions (maker's table; split not stated) |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | multilingual, tokenizer, eval, typed-decisions, encoder | LICENSE, NOTICE |
| Size of latest version | 2.2 GB | 1.2 GB |
| Files | 19 | 12 |
| Downloads | 419 | 1 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, rlcd, multilingual, 421m | system-one, pointer-head, multilingual, indic, 649m |
| Updated | Nov 19, 2026 | Oct 7, 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.
laya is from Convai Innovations and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. lumma-fev reads up to 8K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 649M.
Only lumma-fev publishes an accuracy figure (64.0% on typed-decisions (maker's table; split not stated)); laya does not, so there is no comparison to make without your own test.
laya: Free (open weights). lumma-fev: 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 lumma-fev in about 45.8 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya and systemone pull frontiersmind/lumma-fev download the weights.