Loading profile…
Native MLX FP16 conversion of Laya for Apple silicon. The same ModernBERT-large encoder, decision transformer and heads, running in MLX with no PyTorch; the checkpoint Laya Studio fine-tunes from.
A 512-token context, and the choice, score and noul question types. Loads with the laya-mlx runtime on macOS 14+ with Python 3.11+: laya.load("aac6fef/laya-mlx"). Every model trained in Laya Studio on the English base names this checkpoint as its base.
| Parameters | 421M |
| Base model | convai-innovations/laya |
| Maker | aac6fef |
| Released | 2026-09-19 |
| License | apache-2.0 |
pip install systemonemodels
systemone pull aac6fef/laya-mlx
The files are served from the maker's Hugging Face repository, aac6fef/laya-mlx, and verified against the checksums recorded here.
This page was opened by System One for aac6fef, who can claim the organisation and take it over at any time.
systemone pull aac6fef/laya-mlx.{
"spec_version": "0.1",
"model": "laya-mlx",
"namespace": "aac6fef",
"category": "system-one",
"architecture": "laya",
"base_model": "convai-innovations/laya",
"base_model_source": "huggingface",
"license": "apache-2.0",
"license_name": null,
"summary": "Native MLX FP16 conversion of Laya for Apple silicon. The same ModernBERT-large encoder, decision transformer and heads, running in MLX with no PyTorch; the checkpoint Laya Studio fine-tunes from.",
"tags": [
"system-one",
"mlx",
"apple-silicon",
"modernbert",
"conversion",
"421m"
],
"capabilities": [
"choice",
"score",
"noul"
],
"runtime": {
"framework": "mlx",
"entrypoint": null,
"python": null,
"hardware": "cpu"
},
"artifacts": [],
"evaluation": null,
"parameters": 421000000,
"context_length": 512,
"hub_repo": "aac6fef/laya-mlx",
"released": "2026-09-19",
"availability": "open-weights",
"hosted": null
}View raw metadata