Instructions to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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 "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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": "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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 "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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 ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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 "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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 "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-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"

MLX LM

How to use ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 (MLX 4-bit)

A 4-bit MLX quantization of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2, optimized for Apple Silicon.

About the Base Model

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 is the second iteration of the reasoning-focused Qwen3.5-27B fine-tune. It's built on top of Qwen3.5-27B and fine-tuned with Unsloth using distilled reasoning data from Claude 4.6 Opus. This model has been #1 trending on HuggingFace for 3 weeks.

Key improvements in v2:

More efficient chain-of-thought generation
Improved reasoning across science, math, and instruction-following
Trained on data from Jackrong/Qwen3.5-reasoning-700x

Why MLX?

MLX is Apple's native machine learning framework for Apple Silicon. On an M1 Ultra Mac Studio (128GB), this model runs at 28.9 tokens/sec compared to 19.9 tok/s for the equivalent GGUF Q4_K_M. That's a 45% speed improvement for free, just by using the right format for your hardware.

Benchmark Results

Controlled test: LM Studio, one model loaded at a time, 10 runs each with different prompts, 512 max tokens.

Format	Avg tok/s	Std Dev	Min	Max
MLX 4-bit	28.9	0.11	28.8	29.1
GGUF Q4_K_M	19.9	0.03	19.9	19.9

Hardware: M1 Ultra, 128GB unified memory.

How to Use

LM Studio

Download and place in your LM Studio models directory. LM Studio auto-detects MLX models.

mlx-lm CLI

pip install mlx-lm
mlx_lm.generate --model ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit --prompt "Your prompt here"

mlx-lm Server (OpenAI-compatible API)

mlx_lm.server --model ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit --port 8080

Conversion Details

Quantization: 4-bit (4.501 bits per weight)
Tool: mlx-lm 0.31.1 via mlx_lm.convert
Size: ~14GB
RAM required: ~16GB (fits comfortably on any Apple Silicon Mac with 16GB+ unified memory)

mlx_lm.convert \
  --hf-path Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 \
  -q --q-bits 4 \
  --mlx-path ./output

Note: Requires mlx-lm >= 0.31.1. Earlier versions don't support the qwen3_5 architecture.

Credits

Base model: Jackrong for the Opus distillation
Training framework: Unsloth
MLX framework: Apple MLX team
Conversion: ronnie3786

Downloads last month: 62

Safetensors

Model size

27B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit

Base model

Qwen/Qwen3.5-27B

Adapter

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2

Quantized

(22)

this model