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: 4,333 Bytes

da35640

<svg viewBox="0 0 820 440" xmlns="http://www.w3.org/2000/svg" font-family="system-ui,-apple-system,Segoe UI,Roboto,sans-serif"><rect width="820" height="440" rx="14" fill="#0d1117"/><rect x="1" y="1" width="818" height="438" rx="13" fill="none" stroke="#30363d"/><text x="28" y="40" fill="#e6edf3" font-size="21" font-weight="700">Per-category TTFT &amp; MTP draft acceptance</text><text x="28" y="63" fill="#8b949e" font-size="12.5">FP4 · TTFT = prefill latency (varies with prompt length) · acceptance drives MTP speedup</text><rect x="560" y="31" width="11" height="11" rx="2" fill="#818cf8"/><text x="576" y="40" fill="#8b949e" font-size="11.5">TTFT (ms)</text><rect x="645" y="31" width="11" height="11" rx="2" fill="#34d399"/><text x="661" y="40" fill="#8b949e" font-size="11.5">accept %</text><line x1="70" y1="360" x2="790" y2="360" stroke="#30363d"/><text x="62" y="364" fill="#8b949e" font-size="10" text-anchor="end">0</text><line x1="70" y1="277" x2="790" y2="277" stroke="#30363d"/><text x="62" y="281" fill="#8b949e" font-size="10" text-anchor="end">378</text><line x1="70" y1="193" x2="790" y2="193" stroke="#30363d"/><text x="62" y="197" fill="#8b949e" font-size="10" text-anchor="end">755</text><line x1="70" y1="110" x2="790" y2="110" stroke="#30363d"/><text x="62" y="114" fill="#8b949e" font-size="10" text-anchor="end">1132</text><rect x="109.6" y="225.3" width="40.8" height="134.7" rx="3" fill="#818cf8" opacity="0.85"/><text x="130.0" y="219.3" fill="#e6edf3" font-size="11" text-anchor="middle">610</text><text x="130.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Code</text><rect x="229.6" y="224.7" width="40.8" height="135.3" rx="3" fill="#818cf8" opacity="0.85"/><text x="250.0" y="218.7" fill="#e6edf3" font-size="11" text-anchor="middle">613</text><text x="250.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Math</text><rect x="349.6" y="160.0" width="40.8" height="200.0" rx="3" fill="#818cf8" opacity="0.85"/><text x="370.0" y="154.0" fill="#e6edf3" font-size="11" text-anchor="middle">906</text><text x="370.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Reasoning</text><rect x="469.6" y="222.0" width="40.8" height="138.0" rx="3" fill="#818cf8" opacity="0.85"/><text x="490.0" y="216.0" fill="#e6edf3" font-size="11" text-anchor="middle">625</text><text x="490.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Creative</text><rect x="589.6" y="224.9" width="40.8" height="135.1" rx="3" fill="#818cf8" opacity="0.85"/><text x="610.0" y="218.9" fill="#e6edf3" font-size="11" text-anchor="middle">612</text><text x="610.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Knowledge</text><rect x="709.6" y="226.9" width="40.8" height="133.1" rx="3" fill="#818cf8" opacity="0.85"/><text x="730.0" y="220.9" fill="#e6edf3" font-size="11" text-anchor="middle">603</text><text x="730.0" y="380" fill="#e6edf3" font-size="12.5" text-anchor="middle" font-weight="600">Chat</text><path d="M130.0,147.2 L250.0,134.8 L370.0,154.8 L490.0,175.2 L610.0,150.2 L730.0,192.2" fill="none" stroke="#34d399" stroke-width="2.5"/><circle cx="130.0" cy="147.2" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="130.0" y="137.2" fill="#34d399" font-size="10.5" text-anchor="middle">85%</text><circle cx="250.0" cy="134.8" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="250.0" y="124.8" fill="#34d399" font-size="10.5" text-anchor="middle">90%</text><circle cx="370.0" cy="154.8" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="370.0" y="144.8" fill="#34d399" font-size="10.5" text-anchor="middle">82%</text><circle cx="490.0" cy="175.2" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="490.0" y="165.2" fill="#34d399" font-size="10.5" text-anchor="middle">74%</text><circle cx="610.0" cy="150.2" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="610.0" y="140.2" fill="#34d399" font-size="10.5" text-anchor="middle">84%</text><circle cx="730.0" cy="192.2" r="5" fill="#34d399" stroke="#0d1117" stroke-width="2"/><text x="730.0" y="182.2" fill="#34d399" font-size="10.5" text-anchor="middle">67%</text><text x="70" y="98" fill="#8b949e" font-size="10">ms / %</text></svg>