Laya-Multilingual-MXFP4
laya fine-tuned to return typed decisions, 307M parameters.
Community card
What this is
Laya-Multilingual-MXFP4 is a typed-decision model: given a document and a closed set of options, it returns one of those options with a probability across the whole set rather than free text.
How to run it
MLX on Apple Silicon
MLX uses the unified memory on M-series chips, which is the fastest local option on a Mac. Full MLX on Apple Silicon guide.
mlx_lm.generate --model sahilchachra/Laya-Multilingual-MXFP4A public number is a shortlist, not a decision
The only benchmark that settles which model you ship is one built from your own historical decisions. We freeze that test set, run the candidates against it, and hand back the threshold your error budget supports.