Instructions to use HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-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("HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit")
config = load_config("HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-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

Unsloth Studio

How to use HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit",
    max_seq_length=2048,
)

How to use HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-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 "HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-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": "HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-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 "HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-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 HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit

Run Hermes

hermes

Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit

A distilled version of Qwen3.5-27B, enhanced with Claude Opus 4.6 reasoning patterns through knowledge distillation.

Model Details

Original Model: Qwen/Qwen3.5-27B
Quantization: 4-bit (~4.501 bits per weight)
Group Size: 64
Format: MLX SafeTensors
Framework: mlx-lm

Evaluation Results

Evaluator: Qwen3-Coder-Next
Test Samples: 260 (based on personal dataset, for reference only)
Date: 2026-03-29

Overall Performance

Metric	Base Model	Distilled Model	Improvement
Win Rate	25.77%	73.85%	+48.08%
Avg Latency (s)	71.70	68.47	-4.5%

Score Breakdown (10-point scale)

Dimension	Base Model	Distilled Model	Improvement
Accuracy	6.35	8.59	+35.3%
Logic	6.47	8.69	+34.3%
Completeness	5.70	8.82	+54.7%
Clarity	6.51	8.43	+29.5%
Actionability	5.85	8.56	+46.3%

Performance by Category

Category	Base Win Rate	Distilled Win Rate	Samples
debug	22.67%	76.00%	75
design	51.32%	48.68%	76
prompt	5.80%	94.20%	69
reasoning	17.50%	82.50%	40

Quick Start with oMLX

Installation

brew tap jundot/omlx https://github.com/jundot/omlx
brew install omlx

Alternatively, you can download the DMG version here:

https://github.com/jundot/omlx/releases/tag/v0.3.0

In another terminal, use the API

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "default",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is the capital of France?"}
        ],
        "temperature": 0.7,
        "max_tokens": 256
    }'

License

This model is licensed under Apache-2.0.

This model was distilled to capture Claude Opus 4.6's reasoning capabilities while maintaining Qwen3.5-27B's efficiency and multilingual support. Recommended for inference with vLLM for optimal performance.

Downloads last month: 17

Safetensors

Model size

27B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit

Base model

Qwen/Qwen3.5-27B

Quantized

(210)

this model