Instructions to use mad-lab-ai/Qwen3.6-27B-tq-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
# Run inference directly in the terminal:
llama cli -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
# Run inference directly in the terminal:
llama cli -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

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 mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
# Run inference directly in the terminal:
./llama-cli -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

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 mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

Use Docker

docker model run hf.co/mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

LM Studio
Jan

vLLM

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mad-lab-ai/Qwen3.6-27B-tq-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mad-lab-ai/Qwen3.6-27B-tq-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

Ollama
How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with Ollama:
```
ollama run hf.co/mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
```

Unsloth Studio

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf 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 mad-lab-ai/Qwen3.6-27B-tq-gguf 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 mad-lab-ai/Qwen3.6-27B-tq-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mad-lab-ai/Qwen3.6-27B-tq-gguf to start chatting

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

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": "mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

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 mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

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 "mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with Docker Model Runner:
```
docker model run hf.co/mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0
```

Lemonade

How to use mad-lab-ai/Qwen3.6-27B-tq-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mad-lab-ai/Qwen3.6-27B-tq-gguf:TQ1_0

Run and chat with the model

lemonade run user.Qwen3.6-27B-tq-gguf-TQ1_0

List all available models

lemonade list

Qwen3.6-27B-tq-gguf / README.md

mad-lab-ai

Update README.md

0e784fe verified 3 months ago

preview code

Raw

History Blame Contribute Delete

6.4 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen3.6-27B
base_model_relation: quantized
language:
  - en
tags:
  - gguf
  - quantized
  - tq1_0
  - tq2_0
  - tq3_1s
  - tq4_1s
  - turbo-quant
  - llama.cpp
  - rocm
  - amd
  - qwen3
  - qwen3.6
  - coding
  - imatrix
pipeline_tag: text-generation
library_name: gguf

Qwen3.6-27B TQ (Turbo Quant GGUF)

Full suite of WHT-rotated turbo quant GGUFs for Qwen/Qwen3.6-27B,
quantized with imatrix calibration on Python coding data. Day-of-release quants.

About Turbo Quants

Turbo quants use Walsh-Hadamard Transform rotation before quantization, significantly reducing quantization error versus standard GGUF quants at the same bit width. TQ3_1S and TQ4_1S consistently outperform their Q4/Q5 equivalents. TQ1_0 and TQ2_0 use
ternarization and outperform standard IQ1/IQ2 formats.

Quant Details

File	Format	Type	Size	bpw
Qwen3.6-27B-TQ1_0.gguf	TQ1_0	Ternarization	~5.7GB	1.69
Qwen3.6-27B-TQ2_0.gguf	TQ2_0	Ternarization	~7GB	2.06
Qwen3.6-27B-TQ3_1S.gguf	TQ3_1S	WHT-rotated	~13.5GB	4.00
Qwen3.6-27B-TQ4_1S.gguf	TQ4_1S	WHT-rotated	~17GB	5.00

Quantized using a custom llama.cpp fork with
optimized ROCm/HIP TQ kernel support. Imatrix calibrated on ~1500 Python coding examples sampled from:

ajibawa-2023/Python-Code-23k-ShareGPT
iamtarun/python_code_instructions_18k_alpaca
flytech/python-codes-25k

Usage

llama-server \
  --model Qwen3.6-27B-TQ4_1S.gguf \
  -ngl 999 \
  --ctx-size 32768 \
  --cache-type-k q8_0 \                                                                                                                    
  --cache-type-v q8_0 \
  --flash-attn \                                                                                                                           
  --no-mmap     

Speculative Decoding                                                                                                                       
 
Qwen3.6-27B shares tokenizer (n_vocab=248320) and architecture family (qwen35) with                                                        
Qwen3.5 models, making them compatible for speculative decoding. Pair with a Qwen3.5
draft model for accelerated inference:                                                                                                     
                
llama-server \
  --model Qwen3.6-27B-TQ4_1S.gguf \
  --model-draft Qwen3.5-9B-TQ3_1S.gguf \                                                                                                   
  -ngl 999 -ngld 999 \
  --parallel 1 \                                                                                                                           
  --draft-max 12 --draft-p-min 0.75 \
  --flash-attn --no-mmap                                                                                                                   
                
Hardware Tested                                                                                                                            
 
- AMD Radeon AI PRO R9700 (32GB, gfx1201 RDNA4) via ROCm