Instructions to use aaardpark/Qwen3.6-27B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaardpark/Qwen3.6-27B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aaardpark/Qwen3.6-27B-GGUF",
	filename="qwen3.6-27B-aaardpark-uniform-Q3_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use aaardpark/Qwen3.6-27B-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 aaardpark/Qwen3.6-27B-GGUF
# Run inference directly in the terminal:
llama cli -hf aaardpark/Qwen3.6-27B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aaardpark/Qwen3.6-27B-GGUF
# Run inference directly in the terminal:
llama cli -hf aaardpark/Qwen3.6-27B-GGUF

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 aaardpark/Qwen3.6-27B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf aaardpark/Qwen3.6-27B-GGUF

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 aaardpark/Qwen3.6-27B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aaardpark/Qwen3.6-27B-GGUF

Use Docker

docker model run hf.co/aaardpark/Qwen3.6-27B-GGUF

LM Studio
Jan
Ollama
How to use aaardpark/Qwen3.6-27B-GGUF with Ollama:
```
ollama run hf.co/aaardpark/Qwen3.6-27B-GGUF
```

Unsloth Studio

How to use aaardpark/Qwen3.6-27B-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 aaardpark/Qwen3.6-27B-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 aaardpark/Qwen3.6-27B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aaardpark/Qwen3.6-27B-GGUF to start chatting

How to use aaardpark/Qwen3.6-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaardpark/Qwen3.6-27B-GGUF

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": "aaardpark/Qwen3.6-27B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aaardpark/Qwen3.6-27B-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 aaardpark/Qwen3.6-27B-GGUF

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 aaardpark/Qwen3.6-27B-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use aaardpark/Qwen3.6-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/aaardpark/Qwen3.6-27B-GGUF
```

Lemonade

How to use aaardpark/Qwen3.6-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aaardpark/Qwen3.6-27B-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-27B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-27B | aard-Q3

11 GB of Qwen 3.6-27B

	GSM8K (50 problems, 5-shot)
FP16 (full precision)	49 / 50 = 98%
aard-Q3 (this file)	47 / 50 = 94%

96% of the model's reasoning capacity carries through 3-bit compression.

Why this 3-bit pack isn't bad

I've been messing around with a new quant method that handles 3 bit pretty well by using a different way of preserving important weights.

Three sample outputs

Math:

Q: What is 5/8 of 2/3?

A: To find 5/8 of 2/3, multiply the two fractions: 5/8 × 2/3 = (5 × 2)/(8 × 3) = 10/24 = 5/12.

Factual:

Q: What year did the Treaty of Westphalia end the Thirty Years' War, and name two of its key provisions.

A: The Peace of Westphalia was signed in 1648, ending the Thirty Years' War. Two key provisions:

State sovereignty — each state had exclusive right to govern its internal affairs (religion and military), laying the foundation for the modern sovereign-state system.

Religious tolerance — extended the Peace of Augsburg to recognize Calvinism alongside Lutheranism and Catholicism, ending decades of religious warfare in the Holy Roman Empire.

Code debug:

Q: Find the bug in this Python:
def merge(a, b):
    result = []
    i, j = 0, 0
    while i < len(a) and j < len(b):
        if a[i] < b[j]:
            result.append(a[i])
            i += 1
        else:
            result.append(b[j])
            i += 1
    result.extend(a[i:])
    result.extend(b[j:])
    return result
A: The bug is in the else branch. When a[i] >= b[j], the code appends b[j] but increments i instead of j. The wrong pointer advances, later iterations re-read b[j], and the function eventually walks off the end of a. Fix: change i += 1 in the else branch to j += 1.

Quick stats


File	`qwen3.6-27B-aaardpark-uniform-Q3_K.gguf`
Size	11 GB
Format	GGUF, uniform Q3_K (497 × Q3_K + 1 × Q6_K, 3.59 BPW)
Min VRAM	16 GB
Throughput	~30 tok/s on Apple M-series
Native context	262K (Gated Delta Net linear attention)

Run it

huggingface-cli download aaardpark/Qwen3.6-27B-GGUF \
  qwen3.6-27B-aaardpark-uniform-Q3_K.gguf --local-dir .

llama-cli -m qwen3.6-27B-aaardpark-uniform-Q3_K.gguf -ngl 99 -c 32768

Qwen 3.6 is a thinking model — it emits a <think>…</think> block before the final answer. Budget at least 2048 tokens (4096 for hard reasoning), or set enable_thinking=False if your runtime supports it. Needs llama.cpp build 8670 or later.

Model tree for aaardpark/Qwen3.6-27B-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(522)

this model

aaardpark
/

Qwen3.6-27B-GGUF