Instructions to use mlx-community/diffusiongemma-26B-A4B-it-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/diffusiongemma-26B-A4B-it-4bit 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("mlx-community/diffusiongemma-26B-A4B-it-4bit")
config = load_config("mlx-community/diffusiongemma-26B-A4B-it-4bit")

# 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 mlx-community/diffusiongemma-26B-A4B-it-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/diffusiongemma-26B-A4B-it-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/diffusiongemma-26B-A4B-it-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/diffusiongemma-26B-A4B-it-4bit 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 "mlx-community/diffusiongemma-26B-A4B-it-4bit"

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 mlx-community/diffusiongemma-26B-A4B-it-4bit

Run Hermes

hermes

OpenClaw new

How to use mlx-community/diffusiongemma-26B-A4B-it-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/diffusiongemma-26B-A4B-it-4bit"

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 "mlx-community/diffusiongemma-26B-A4B-it-4bit" \
  --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"

diffusion_gemma not supported?

by jasonw22 - opened 29 days ago

Discussion

jasonw22

29 days ago

Getting an error: ERROR:root:Model type diffusion_gemma not supported.

weightsnweights

28 days ago

Getting the same error

usermma

28 days ago

just upgrade your version...

AdamDevelopment

27 days ago

I'm using LM studio/oMLX, upgraded LM Studio but still don't work

johndpope

21 days ago

•

edited 21 days ago

did it help?
pip install -U mlx-vlm

UPDATE 1.
same problem - going to try this one instead
https://huggingface.co/mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit

UPDATE 2.
seems to be working

mlx_vlm.server --model "mlx-community/diffusiongemma-26B-A4B-it-4bit"

INFO: Started server process [5141]
INFO: Waiting for application startup.
2026-06-19 17:42:07,167 - INFO - Pre-loading model: mlx-community/diffusiongemma-26B-A4B-it-4bit
Loading model from: mlx-community/diffusiongemma-26B-A4B-it-4bit
2026-06-19 17:42:07,647 - INFO - HTTP Request: GET https://huggingface.co/api/models/mlx-community/diffusiongemma-26B-A4B-it-4bit/revision/main "HTTP/1.1 200 OK"
Fetching 11 files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 11/11 [00:00<00:00, 21067.28it/s]
Download complete: : 0.00B [00:00, ?B/s] | 0/11 [00:00<?, ?it/s]
Model and processor loaded successfully.
2026-06-19 17:42:32,630 - INFO - Model ready, continuous batching enabled.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)

strangely - doesnt actually respond -

trying this

python -m mlx_vlm.server --model "mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit"

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment