Instructions to use macwhisperer/Qwen3.6-35B-SuperMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macwhisperer/Qwen3.6-35B-SuperMoE with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="macwhisperer/Qwen3.6-35B-SuperMoE",
	filename="Qwen-3.6-35B-MoE-Imatrix-IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use macwhisperer/Qwen3.6-35B-SuperMoE with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Use Docker

docker model run hf.co/macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

LM Studio
Jan
Ollama
How to use macwhisperer/Qwen3.6-35B-SuperMoE with Ollama:
```
ollama run hf.co/macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
```

Unsloth Studio new

How to use macwhisperer/Qwen3.6-35B-SuperMoE 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 macwhisperer/Qwen3.6-35B-SuperMoE 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 macwhisperer/Qwen3.6-35B-SuperMoE to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for macwhisperer/Qwen3.6-35B-SuperMoE to start chatting

Pi new

How to use macwhisperer/Qwen3.6-35B-SuperMoE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use macwhisperer/Qwen3.6-35B-SuperMoE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

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 macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Run Hermes

hermes

Docker Model Runner
How to use macwhisperer/Qwen3.6-35B-SuperMoE with Docker Model Runner:
```
docker model run hf.co/macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M
```

Lemonade

How to use macwhisperer/Qwen3.6-35B-SuperMoE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull macwhisperer/Qwen3.6-35B-SuperMoE:IQ3_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-SuperMoE-IQ3_M

List all available models

lemonade list

📟 Qwen3.6-35B-MoE-Imatrix-IQ3_M.gguf (2026 Edition)

"Local intelligence... to the max."

This is a custom-quantized version of Qwen3.6-35B-A3B, specifically optimized to obtain the highest possible local byte-intelligence ratio with 24GB+ RAM consumer laptops or computers.

🧠 Why this model is different

Unlike a standard quant, this model was processed using a custom Importance Matrix (imatrix). The training data for the imatrix was hand-curated to preserve:

Incredible reasoning: Inclusion of custom coding examples built with frontier models provides high retention of very specific and sharp architectural reasoning skills
Logical Flow: Inclusion of llama.cpp source code, logic puzzles, and historical writing in the imatrix training to ensure the model stays coherent at low bitrates.
High Speed: Built using llama.cpp specifically for local-first AI and edge computing setups like apple silicon with minimum 24GB RAM

🛠 Quantization Details

Base Model: Qwen3.6-35B-A3B
Quantization: IQ3_M
Format: GGUF
Size: ~15.44 GB
Context Length: 262144 tokens

📈 Perplexity Benchmarks

The following results were generated using llama-perplexity on the wikitext-2-raw/wiki.test.raw dataset.

Model	Precision	Perplexity (PPL)	Δ PPL
Qwen3.6-35B-A3B- (no-imatrix)	IQ3_M	8.3352	-
Qwen3.6-35b-A3B- (Imatrix)	IQ3_M	7.0862	-1.249

⚖️ Evaluation Verdict

The IQ3_M (Imatrix) delivers performance closer to 4-bit quants while maintaining the memory footprint of a 3-bit model. In the context of PPL, lower is better. It measures the model's "uncertainty" when predicting the next token. A delta of -1.249 at this scale indicates that the I-Matrix successfully mitigated the quantization noise that usually plagues sub-4-bit models.