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.
Native MLX FP16 conversion of Laya's multilingual checkpoint (mmBERT) for Apple silicon, with a 1,024-token context. The base for multilingual fine-tunes in Laya Studio.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
laya
laya
Fine-tuned from
answerdotai/modernbert-large
convaiinnovations/laya-multilingual
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
39.5 ms
—
p95 latency
—
—
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.
Questions
What is the difference between laya and laya-multilingual-mlx?
laya is from Convai Innovations and laya-multilingual-mlx from aac6fef. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. laya-multilingual-mlx reads up to 1K tokens of state, against 512 tokens for laya. laya-multilingual-mlx is the smaller model, at 322M parameters to 421M.
Which is more accurate, laya or laya-multilingual-mlx?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya or laya-multilingual-mlx?
laya: Free (open weights). laya-multilingual-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya or laya-multilingual-mlx locally?
Yes, both: systemone pull convai-innovations/laya and systemone pull aac6fef/laya-multilingual-mlx download the weights.
