Instructions to use modilify/Modilify-Mk1-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modilify/Modilify-Mk1-MLX with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("modilify/Modilify-Mk1-MLX")
config = load_config("modilify/Modilify-Mk1-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use modilify/Modilify-Mk1-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "modilify/Modilify-Mk1-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "modilify/Modilify-Mk1-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use modilify/Modilify-Mk1-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "modilify/Modilify-Mk1-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default modilify/Modilify-Mk1-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use modilify/Modilify-Mk1-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "modilify/Modilify-Mk1-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "modilify/Modilify-Mk1-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Modilify-Mk1-MLX / README.md

ydy9038074

Publish Modilify Mk1 MLX runtime

a066584 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

2.25 kB

	---
	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.