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

Libraries

How to use unsloth/Qwen3.6-27B-MTP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="unsloth/Qwen3.6-27B-MTP-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Qwen3.6-27B-MTP-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Qwen3.6-27B-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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.6-27B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.6-27B-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": "unsloth/Qwen3.6-27B-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Qwen3.6-27B-MTP-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/Qwen3.6-27B-MTP-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3.6-27B-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/Qwen3.6-27B-MTP-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3.6-27B-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use unsloth/Qwen3.6-27B-MTP-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use unsloth/Qwen3.6-27B-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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3.6-27B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.6-27B-MTP-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Qwen3.6-27B-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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Qwen3.6-27B-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL

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 "unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q4_K_XL" \
  --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"

FYI : --spec-type mtp syntax has changed to --spec-type draft-mtp

#14

by qenme - opened May 14

Discussion

qenme

May 14

The --spec-type mtp syntax has changed to --spec-type draft-mtp for the branch.

That is all :)

danielhanchen

Unsloth AI org May 15

Hello you are correct, we will need to change our guides and model cards with the updated instructions.

owao

May 15

•

edited May 15

--presence-penalty 1.5 for thinking mode also needs updating, official recommendation says 0 now (for the 3.6-27B, 3.6-36A3B different settings)

Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
Thinking mode for precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

@danielhanchen what you have against me? Was it about my drama toward Mistral? Oh no ok I think I remember... About my arsh tone when you previously often reuploaded new weights without changelogs? If it's coming from there I'm indeed sorry for the tone I had... Got a bit emotional at that time around this topic...
But if you actually see me as a bad, ungrateful guy, that's not the case. I just sometimes have difficulties with communication and often take the vilain role to say things loud for the mass. I guess that's also why I don't find it fair to make me pay it all. I also try to help ppl whenever I can with my limited knowledge, and paying that much for something I almost never do feels unfair to me.
Again I apologize for the tone I had. Can you forgive me and allow me to contribute again peacefully as I can in the future like... give me a second chance?

By the way, I watch your whole presentation about quantization and I liked it and wanted to say thanks! And beyond that, thanks for all the work you do for the community and democratizing training. You are the ones doing it just by genuine generosity expecting nothing in return, and this act of love is pure and beautiful...

qenme

May 16

•

edited May 16

--presence-penalty 1.5 for thinking mode also needs updating, official recommendation says 0 now (for the 3.6-27B, 3.6-36A3B different settings)

Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
Thinking mode for precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

@danielhanchen what you have against me? Was it about my drama toward Mistral? Oh no ok I think I remember... About my arsh tone when you previously often reuploaded new weights without changelogs? If it's coming from there I'm indeed sorry for the tone I had... Got a bit emotional at that time around this topic...
But if you actually see me as a bad, ungrateful guy, that's not the case. I just sometimes have difficulties with communication and often take the vilain role to say things loud for the mass. I guess that's also why I don't find it fair to make me pay it all. I also try to help ppl whenever I can with my limited knowledge, and paying that much for something I almost never do feels unfair to me.
Again I apologize for the tone I had. Can you forgive me and allow me to contribute again peacefully as I can in the future like... give me a second chance?

By the way, I watch your whole presentation about quantization and I liked it and wanted to say thanks! And beyond that, thanks for all the work you do for the community and democratizing training. You are the ones doing it just by genuine generosity expecting nothing in return, and this act of love is pure and beautiful...

Sometimes we make assumptions about how someone else is thinking or feeling without there ever being any real evidence for it. I am guilty of this too. Everyone has things on their mind and they make not be thinking the same exact way. I'm sure he doesn't actually have anything against you, he's just busy trying to survive like all of us.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment