Instructions to use AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4 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("AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4")
config = load_config("AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4")

# 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 AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4"

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": "AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4 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 "AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4"

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 AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4

Run Hermes

hermes

OpenClaw new

How to use AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4"

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 "AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4" \
  --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"

Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-FP4

File size: 4,024 Bytes

da35640

<svg viewBox="0 0 760 430" xmlns="http://www.w3.org/2000/svg" font-family="system-ui,-apple-system,Segoe UI,Roboto,sans-serif"><rect width="760" height="430" rx="14" fill="#0d1117"/><rect x="1" y="1" width="758" height="428" rx="13" fill="none" stroke="#30363d"/><text x="28" y="42" fill="#e6edf3" font-size="22" font-weight="700">Decode throughput &amp; memory footprint</text><text x="28" y="66" fill="#8b949e" font-size="13">tokens/sec (single stream) · peak unified memory · M4 Pro 48 GB</text><text x="70" y="108" fill="#8b949e" font-size="12" font-weight="600">DECODE SPEED</text><line x1="70" y1="360" x2="350" y2="360" stroke="#30363d" stroke-width="1"/><text x="62" y="364" fill="#8b949e" font-size="10" text-anchor="end">0</text><line x1="70" y1="302" x2="350" y2="302" stroke="#30363d" stroke-width="1"/><text x="62" y="306" fill="#8b949e" font-size="10" text-anchor="end">7</text><line x1="70" y1="245" x2="350" y2="245" stroke="#30363d" stroke-width="1"/><text x="62" y="249" fill="#8b949e" font-size="10" text-anchor="end">14</text><line x1="70" y1="188" x2="350" y2="188" stroke="#30363d" stroke-width="1"/><text x="62" y="192" fill="#8b949e" font-size="10" text-anchor="end">21</text><line x1="70" y1="130" x2="350" y2="130" stroke="#30363d" stroke-width="1"/><text x="62" y="134" fill="#8b949e" font-size="10" text-anchor="end">28</text><rect x="93.3" y="292.6" width="46.7" height="67.4" rx="4" fill="#818cf8"/><text x="116.7" y="284.6" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">8.2</text><text x="116.7" y="378" fill="#8b949e" font-size="11" text-anchor="middle">MLX-8bit</text><rect x="186.7" y="235.1" width="46.7" height="124.9" rx="4" fill="#fbbf24"/><text x="210.0" y="227.1" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">15.2</text><text x="210.0" y="378" fill="#8b949e" font-size="11" text-anchor="middle">MLX-FP4</text><rect x="280.0" y="142.3" width="46.7" height="217.7" rx="4" fill="#34d399"/><text x="303.3" y="134.3" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">26.5</text><text x="303.3" y="378" fill="#8b949e" font-size="11" text-anchor="middle">FP4 + MTP</text><text x="350" y="378" fill="#8b949e" font-size="10" text-anchor="end">tok/s</text><text x="440" y="108" fill="#8b949e" font-size="12" font-weight="600">PEAK MEMORY</text><line x1="440" y1="360" x2="720" y2="360" stroke="#30363d" stroke-width="1"/><text x="432" y="364" fill="#8b949e" font-size="10" text-anchor="end">0</text><line x1="440" y1="302" x2="720" y2="302" stroke="#30363d" stroke-width="1"/><text x="432" y="306" fill="#8b949e" font-size="10" text-anchor="end">8</text><line x1="440" y1="245" x2="720" y2="245" stroke="#30363d" stroke-width="1"/><text x="432" y="249" fill="#8b949e" font-size="10" text-anchor="end">16</text><line x1="440" y1="188" x2="720" y2="188" stroke="#30363d" stroke-width="1"/><text x="432" y="192" fill="#8b949e" font-size="10" text-anchor="end">24</text><line x1="440" y1="130" x2="720" y2="130" stroke="#30363d" stroke-width="1"/><text x="432" y="134" fill="#8b949e" font-size="10" text-anchor="end">32</text><rect x="463.3" y="145.1" width="46.7" height="214.9" rx="4" fill="#818cf8"/><text x="486.7" y="137.1" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">29.9</text><text x="486.7" y="378" fill="#8b949e" font-size="11" text-anchor="middle">MLX-8bit</text><rect x="556.7" y="237.1" width="46.7" height="122.9" rx="4" fill="#fbbf24"/><text x="580.0" y="229.1" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">17.1</text><text x="580.0" y="378" fill="#8b949e" font-size="11" text-anchor="middle">MLX-FP4</text><rect x="650.0" y="225.6" width="46.7" height="134.4" rx="4" fill="#34d399"/><text x="673.3" y="217.6" fill="#e6edf3" font-size="14" font-weight="700" text-anchor="middle">18.7</text><text x="673.3" y="378" fill="#8b949e" font-size="11" text-anchor="middle">FP4 + MTP</text><text x="720" y="378" fill="#8b949e" font-size="10" text-anchor="end">GB</text></svg>