Instructions to use WaveCut/Qwen3.8-27B-MLX-4bit-DWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WaveCut/Qwen3.8-27B-MLX-4bit-DWQ 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("WaveCut/Qwen3.8-27B-MLX-4bit-DWQ")
config = load_config("WaveCut/Qwen3.8-27B-MLX-4bit-DWQ")

# 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 WaveCut/Qwen3.8-27B-MLX-4bit-DWQ with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "WaveCut/Qwen3.8-27B-MLX-4bit-DWQ"

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": "WaveCut/Qwen3.8-27B-MLX-4bit-DWQ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use WaveCut/Qwen3.8-27B-MLX-4bit-DWQ 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 "WaveCut/Qwen3.8-27B-MLX-4bit-DWQ"

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 WaveCut/Qwen3.8-27B-MLX-4bit-DWQ

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use WaveCut/Qwen3.8-27B-MLX-4bit-DWQ with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "WaveCut/Qwen3.8-27B-MLX-4bit-DWQ"

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 "WaveCut/Qwen3.8-27B-MLX-4bit-DWQ" \
  --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"

Qwen3.8-27B-MLX-4bit-DWQ / evaluation-summary.json

WaveCut

Add files using upload-large-folder tool

8d0b89d verified about 2 months ago

Raw History Blame Contribute Delete

1.16 kB

	{
	"primary_metric": {
	"name": "fixed_holdout_sparse_teacher_kl",
	"lower_is_better": true,
	"baseline": 0.204094,
	"final": 0.074299,
	"relative_improvement_percent": 63.59569610081629,
	"acceptance_threshold": 0.203890,
	"curve": [
	{"examples": 0, "value": 0.204094},
	{"examples": 200, "value": 0.098783},
	{"examples": 400, "value": 0.084881},
	{"examples": 600, "value": 0.080500},
	{"examples": 800, "value": 0.080442},
	{"examples": 1000, "value": 0.075115},
	{"examples": 1024, "value": 0.074299}
	]
	},
	"behavioral_smoke": {
	"thinking_enabled": false,
	"baseline": {"passed": 11, "total": 11, "tool_calling": "2/2", "multilingual": "7/7", "code": "2/2", "mean_prompt_tps": 67.96078813416983, "mean_generation_tps": 23.164060581386426, "peak_memory_gb": 16.053686628},
	"dwq": {"passed": 11, "total": 11, "tool_calling": "2/2", "multilingual": "7/7", "code": "2/2", "mean_prompt_tps": 67.68120081334023, "mean_generation_tps": 23.19472924373464, "peak_memory_gb": 16.053670244}
	},
	"clean_load": {
	"mlx_lm_text": "Варшава",
	"mlx_vlm_image": "Blue"
	}
	}