Instructions to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF",
	filename="Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q4_K_P.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

Use Docker

docker model run hf.co/SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-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": "SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

Ollama
How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with Ollama:
```
ollama run hf.co/SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
```

Unsloth Studio

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF to start chatting

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

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": "SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

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 SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4
```

Lemonade

How to use SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SummonGovernance/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF-NVFP4

List all available models

lemonade list

Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-GGUF

Files

File	Source lineage	Size
`Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q4_K_P.gguf`	MTP `Q4_K_P` source GGUF	15,388,070,304 bytes
`Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q6_K_P.gguf`	MTP `Q6_K_P` source GGUF	15,388,070,368 bytes
`Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q8_K_P.gguf`	MTP `Q8_K_P` source GGUF	15,388,070,368 bytes

Q4_K_P, Q6_K_P, and Q8_K_P describe the source GGUF lineage. The files themselves are NVFP4 GGUF files.

Conversion Summary

All variants preserve the original MTP layer as block 64 and keep F32 tensors as F32.

Q4_K_P-derived artifact

325 Q4_K tensors -> NVFP4
173 Q6_K tensors -> NVFP4
8 Q8_0 tensors  -> NVFP4
360 F32 tensors -> F32

Q6_K_P-derived artifact

374 Q6_K tensors -> NVFP4
132 Q8_0 tensors -> NVFP4
360 F32 tensors  -> F32

Q8_K_P-derived artifact

407 Q8_0 tensors -> NVFP4
99 F16 tensors   -> NVFP4
360 F32 tensors  -> F32

Validation

Each MTP artifact was checked after conversion:

tensor_count = 866
NVFP4 = 506
F32 = 360
qwen35.block_count = 65
qwen35.nextn_predict_layers = 1
mtp_tensors = 15
general.file_type = 39

Optimized Agentic Tooling

Tool-calling on llama.cpp with CUDA 13.3+ using WebUI.

Q8_K_P

llama-server.exe ^
-m "Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q8_K_P.gguf" ^
--jinja ^
--spec-type draft-mtp ^
--spec-draft-n-max 1 ^
--spec-draft-ngl 100 ^
-ngl 100 ^
-np 1 ^
-fa on ^
-c 262144 ^
-ctk q4_0 ^
-ctv q4_0 ^
--context-shift ^
--host 127.0.0.1 ^
--port 8033 ^
--tools read_file,file_glob_search,grep_search,exec_shell_command,write_file,edit_file,apply_diff

Q6_K_P

llama-server.exe ^
-m "Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q6_K_P.gguf" ^
--jinja ^
--spec-type draft-mtp ^
--spec-draft-n-max 1 ^
--spec-draft-ngl 100 ^
-ngl 100 ^
-np 1 ^
-fa on ^
-c 262144 ^
-ctk q4_0 ^
-ctv q4_0 ^
--context-shift ^
--host 127.0.0.1 ^
--port 8033 ^
--tools read_file,file_glob_search,grep_search,exec_shell_command,write_file,edit_file,apply_diff

Q4_K_P

llama-server.exe ^
-m "Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-NVFP4-MTP-Q4_K_P.gguf" ^
--jinja ^
--spec-type draft-mtp ^
--spec-draft-n-max 2 ^
--spec-draft-ngl 100 ^
-ngl 100 ^
-np 1 ^
-fa on ^
-c 262144 ^
-ctk q4_0 ^
-ctv q4_0 ^
--context-shift ^
--host 127.0.0.1 ^
--port 8033 ^
--tools read_file,file_glob_search,grep_search,exec_shell_command,write_file,edit_file,apply_diff

Downloads last month: 1,406

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

6-bit