---
license: other
license_name: modilify-open-model-license-1.0
license_link: LICENSE
library_name: mlx
pipeline_tag: image-text-to-text
base_model: modilify/Modilify-Mk1
tags:
  - mlx
  - diffusion
  - multimodal
  - image-text-to-text
  - mixture-of-experts
---

![LOGO](assets/01-LOGO.jpg)

# Modilify Mk1 MLX

Native MLX runtime for [Modilify Mk1](https://huggingface.co/modilify/Modilify-Mk1).

`model_type` is `modilify_mk1`. This package does not rewrite the checkpoint as another architecture and does not install into oMLX.

The published `model-*.safetensors` shards are a server-side copy of the official Mk1 weights. `modilify_mlx.load` remaps PyTorch parameter names at load time, so you do not need a second converted 49GB checkpoint on the Hub.

## Layout

- `modilify_mlx/` — config, latent deliberation, exclusive commit policy, trunk wrapper, generate loop
- `convert_modilify_mk1_mlx.py` — official safetensors → MLX shards
- `generate_modilify.py` — standalone text trial inference

The heavy decoder / vision trunk is composed from mlx-vlm's DiffusionGemma layers as an internal dependency. Router top-k and the RMS-capped latent merge are Mk1's own forwards.

## Convert

Use the oMLX bundled interpreter only as a Python that already has `mlx`:

```bash
export PYTHONHOME=/Applications/oMLX.app/Contents/Resources/Python/cpython-3.11
export PYTHONPATH=/Applications/oMLX.app/Contents/Resources:/Applications/oMLX.app/Contents/Resources/Python/framework-mlx-base/lib/python3.11/site-packages
/Applications/oMLX.app/Contents/Resources/Python/cpython-3.11/bin/python3 \
  ~/Modilify-Mk1-MLX/convert_modilify_mk1_mlx.py \
  --source ~/Modilify-Mk1 \
  --destination ~/Modilify-Mk1-MLX
```

## Generate

Official Mk1 shards and locally remapped MLX shards both load. Parameter names are remapped in `modilify_mlx.load`.

```bash
/Applications/oMLX.app/Contents/Resources/Python/cpython-3.11/bin/python3 \
  ~/Modilify-Mk1-MLX/generate_modilify.py \
  --model ~/Modilify-Mk1-MLX \
  --prompt "Explain why the sky is blue." \
  --max-new-tokens 128
```

Default is bf16 (`--expert-bits 16`). Add `--profile` to print per-phase denoise timings. Full-graph `mx.compile` of the decoder is blocked by MoE gather/router slices.