Instructions to use MedMLX/MLX-Reason-CT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MedMLX/MLX-Reason-CT 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("MedMLX/MLX-Reason-CT")
config = load_config("MedMLX/MLX-Reason-CT")

# 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 MedMLX/MLX-Reason-CT with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MedMLX/MLX-Reason-CT"

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": "MedMLX/MLX-Reason-CT"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use MedMLX/MLX-Reason-CT 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 "MedMLX/MLX-Reason-CT"

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 MedMLX/MLX-Reason-CT

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MedMLX/MLX-Reason-CT with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MedMLX/MLX-Reason-CT"

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 "MedMLX/MLX-Reason-CT" \
  --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"

MedMLX — Reason. 3D CT / VISION + LANGUAGE

MLX-Reason-CT

Generate reports and ask questions about 3D chest and abdomen CT, locally on Apple Silicon.

GitHub · Files · Docs · Paper

Input	Output
3D CT · NIfTI	Reports and CT question answering

Apple Silicon · Metal · Python 3.13

Quick start

uv venv --python 3.13
source .venv/bin/activate
uv pip install "mlx-reason-ct>=0.7.0"

Replace the example input paths with your own files.

from mlx_reason_ct import run

result = run(image_path="ct.nii.gz", output_dir="outputs")
print(result["details"]["report"])

Weights download from this repository on first use, at a pinned revision. To fetch them yourself, download that revision and pass the folder as weights_path="models":

uv tool install huggingface-hub
hf download MedMLX/MLX-Reason-CT --revision 5e5b5202fd04ac9f63ede203ebc9327aa676ae94 --local-dir models

Set anatomy_region="abdomen" for abdominal CT, or pass prompt to ask a question. Requires mlx-reason-ct; generic mlx-vlm and mlx-lm loaders are incompatible. The bundle is 17.4 GB on disk. Peak MLX memory for a chest or abdomen report is about 12.5 GB; allow more for preprocessing, macOS and other applications.

Use & license

For research and education. Not validated for clinical use.

Weights: OpenMDW-1.1. Notices.

Paper

Original model: NV-Reason-CT: 3D Visual Language Model for CT Analysis.

Citation

If you use MedMLX, please cite the MedMLX paper:

@article{sandoval2026medmlx,
  title   = {MedMLX: On-Device Medical Imaging AI for Apple Silicon},
  author  = {Sandoval, J. and Sandoval, A. and Saleem, A.},
  journal = {medRxiv},
  year    = {2026},
  doi     = {10.64898/2026.10.28.26366762}
}