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.
A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
laya
rizzo-flow
Fine-tuned from
convaiinnovations/laya-multilingual
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
—
195 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-multilingual-mlx and rizzo-flow?
laya-multilingual-mlx is from aac6fef and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score and noul questions. Only rizzo-flow answers classify and route. laya-multilingual-mlx is the smaller model, at 322M parameters to 4.0B.
Which is more accurate, laya-multilingual-mlx or rizzo-flow?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); laya-multilingual-mlx does not, so there is no comparison to make without your own test.
Which is cheaper, laya-multilingual-mlx or rizzo-flow?
laya-multilingual-mlx: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya-multilingual-mlx or rizzo-flow locally?
Yes, both: systemone pull aac6fef/laya-multilingual-mlx and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
—
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
