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.
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
julia
laya
Fine-tuned from
jhu-clsp/mmbert-small
convaiinnovations/laya-multilingual
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
—
—
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 julia-1 and laya-multilingual-mlx?
julia-1 is from Supersonic Labs and laya-multilingual-mlx from aac6fef. Both have open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. julia-1 reads up to 8K tokens of state, against 1K tokens for laya-multilingual-mlx. julia-1 is the smaller model, at 144M parameters to 322M.
Which is more accurate, julia-1 or laya-multilingual-mlx?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); laya-multilingual-mlx does not, so there is no comparison to make without your own test.
Which is cheaper, julia-1 or laya-multilingual-mlx?
julia-1: Free (open weights). laya-multilingual-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or laya-multilingual-mlx locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull aac6fef/laya-multilingual-mlx download the weights.
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
