---
base_model: deepgrove/maple-preview
base_model_relation: quantized
language:
  - en
library_name: mlx
license: mit
pipeline_tag: text-generation
tags:
  - mlx
  - maple
  - mixture-of-experts
  - quantized
  - experimental
  - openmed
---

# Maple Preview 4-bit MLX — experimental archive

> **Do not deploy this export.** It is retained privately as a reproducibility
> artifact for a failed development validation result.

This OpenMed export was converted from
[`deepgrove/maple-preview`](https://huggingface.co/deepgrove/maple-preview)
revision `ac1ddd79d2b5cb4406f5d2bebdf95406ce505a07` with 4-bit affine
quantization and group size 128. The included `openmed-maple-export.json`
records the pinned source and runtime-code revisions and conversion settings.

The checkpoint converted and loaded on Apple Silicon, but its synthetic
structured-task run exhausted the 4,096-token generation budget before
producing final JSON. Successful tensor conversion is not evidence of useful
or safe generation. No clinical-quality, direct-identifier recall,
critical-leakage, source-parity, or physical-device claim is made.

See the validation table and reproducible export instructions in
[`docs/maple-on-device.md`](https://github.com/maziyarpanahi/openmed/blob/master/docs/maple-on-device.md).

Maple Preview is a research model, not a medical device. The upstream model is
licensed under MIT; see the upstream repository for its license and model card.