Instructions to use Duckets/Arete-27B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Duckets/Arete-27B-MLX-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("Duckets/Arete-27B-MLX-4bit")
config = load_config("Duckets/Arete-27B-MLX-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 Duckets/Arete-27B-MLX-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 "Duckets/Arete-27B-MLX-4bit"

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": "Duckets/Arete-27B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Duckets/Arete-27B-MLX-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 "Duckets/Arete-27B-MLX-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 Duckets/Arete-27B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Duckets/Arete-27B-MLX-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 "Duckets/Arete-27B-MLX-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 "Duckets/Arete-27B-MLX-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"

Arete-27B — MLX 4-bit

A 4-bit MLX conversion of Nous Research's Arete-27B (value-alignment SFT of Qwen3.8-27B), for Apple Silicon via MLX / LM Studio.

Credits

Nous Research — creators of Arete-27B, the model converted here.

Conversion

Source: NousResearch/Arete-27B BF16 checkpoint, revision 108f0afbdcfaa1ceeda4a635004304dfff6d4da2.
Converted with mlx_vlm.convert at 4-bit (4.695 bpw). ~15 GiB on disk.

Verified in LM Studio

Loaded and smoke-tested in LM Studio (MLX runtime) on an M5 Max (128 GB):

Reasoning check: 17 × 23 = 391, √169 = 13
Vision check: solid-color image identified correctly ("red")
Speed: 31.2 tok/s decode (single stream, ~60-token prompt, temp 0, default load settings)

A faster Splash-engine package of the same model is available at Duckets/Arete-27B-Splash (104.5 tok/s in LM Studio's Splash runtime).

Usage

Download into your LM Studio models folder (cataloged as arete-27b-mlx), or load directly with mlx-vlm.

License

Apache-2.0, following the source model.

Downloads last month: -

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Duckets/Arete-27B-MLX-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

NousResearch/Arete-27B

Quantized

(29)

this model