Instructions to use wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 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("wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4")

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 wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"

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": "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"

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 "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4" \
  --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 wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 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 "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"

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 wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4

Run Hermes

hermes

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4

Mixed-precision quantization for Apple Silicon, text-only mode (vision tower stripped for faster, lighter inference).

Quantized from lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled using oMLX's oQ4 algorithm (sensitivity-aware mixed-precision quantization).

📊 Specs

Field	Value
Base model	Qwen/Qwen3.6-35B-A3B (35B params, 128 experts MoE, A3B activation)
Fine-tune	LoRA distilled from Claude 4.7 Opus reasoning outputs (lordx64 dataset)
Quantization	oMLX oQ4 (mixed-precision, ~4.8 bpw average)
Modality	Text only (vision tower stripped)
Format	MLX safetensors
Model size	~19 GB
Inference memory	~20 GB (incl. KV cache and runtime overhead)
Recommended hardware	Apple Silicon M2 Pro 32GB+ / M3 Max / M5 Max

🚀 Quick Start

Install

pip install mlx-lm
# Or with uv:
uv tool install mlx-lm

Inference

mlx_lm.generate \
  --model wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 \
  --prompt "Explain mixture of experts in one paragraph." \
  --max-tokens 512

Python API

from mlx_lm import load, generate

model, tokenizer = load(
    "wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4"
)

response = generate(
    model,
    tokenizer,
    prompt="Solve: integrate x*sin(x) dx",
    max_tokens=512,
)
print(response)

OpenAI-compatible Server

mlx_lm.server \
  --model wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4 \
  --port 8080

Drop-in compatible with OpenAI clients including Claude Code (with custom backend), AstrBot, Open WebUI, LibreChat, and Continue.dev.

📈 Measured Performance

Benchmarked on MacBook Pro M5 Max 128GB:

Metric	Value
Prompt processing	~67 tokens/s
Generation speed	~127 tokens/s
Peak memory	20.4 GB
Model load time	~8 sec

Why Text-Only?

Stripping the vision tower offers practical advantages for text-only workflows:

~10% faster generation vs the VLM equivalent (no vision compute path overhead)
~2 GB less peak memory
Simpler deployment — no need for vision processor configs or image preprocessing dependencies

If you only feed text into your model, this version is strictly better than the VLM variant.

🧠 Model Behavior

Inherits the Claude reasoning distillation: the model uses <think>...</think> tags to structure its chain-of-thought before producing the final response.

Best for:

Coding agents and tool-use workflows
Complex reasoning tasks (math, logic, analysis)
Long-form text generation
Scenarios where visible reasoning improves quality

Sample output structure:

<think>
1. Analyze the user's request: ...
2. Identify the key constraints: ...
3. Formulate the solution: ...
</think>

Here is my analysis: ...

🔬 Quantization Details

Source model: Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled (BF16 MLX-converted)
Sensitivity model: 8-bit quantization of the same distilled model (self-referenced sens for tight distribution alignment)
Non-quant weight dtype: bfloat16 (M3+ optimal)
Text-Only mode: ON (vision tower stripped — verified: 0 vision-related tensors)
Quantizer: oMLX

📦 Other Versions in This Series

Version	Size	Best for
VLM-MLX-oQ4	19.6 GB	Memory-constrained inference (with vision)
VLM-MLX-oQ6	27 GB	Recommended VLM quality/size ratio
VLM-MLX-oQ8	35 GB	VLM quality reference baseline
Text-MLX-oQ4	19 GB	Text-only, fastest
Text-MLX-oQ6	27 GB	Recommended text-only
Text-MLX-oQ8	34 GB	Text-only, max quality

Choosing a version:

Text-only workflows (coding, agents, dialogue) → Text variants are faster and lighter
Image input needed (OCR, visual analysis, screenshot understanding) → VLM variants
oQ6 is the sweet spot for most use cases. oQ8 yields diminishing returns relative to its size.

⚠️ Disclaimer

This model derives from a chain of upstream work:

Base model Qwen/Qwen3.6-35B-A3B by Alibaba's Qwen team (Apache-2.0)
Distilled variant lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled by lordx64 using Claude 4.7 Opus reasoning outputs (Apache-2.0)
This quantization by @wangkezun using oMLX on Apple Silicon

This model is not affiliated with or endorsed by Anthropic, PBC. "Claude" is a trademark of Anthropic, PBC. The use of "Claude" in this model name is purely descriptive (nominative fair use) to indicate the upstream training data lineage.

By using this model, you agree to comply with:

The Apache-2.0 license inherited from the base model
Any applicable license terms of the upstream distillation dataset
Local laws and regulations governing AI model usage in your jurisdiction

🙏 Acknowledgments

Alibaba Qwen Team — for the Qwen3.6-35B-A3B base model
lordx64 — for the reasoning-focused LoRA distillation
Jundot (oMLX team) — for the oQ mixed-precision quantization algorithm
Apple MLX team — for the MLX framework and tooling

📜 License

Apache-2.0 (inherited from base model).

Generated: 2026-04-26
Quantizer: @wangkezun

Downloads last month: 65

Safetensors

Model size

6B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ4

Base model

Qwen/Qwen3.6-35B-A3B

Adapter

lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled

Quantized

(45)

this model