Instructions to use unsloth/Qwen3.5-9B-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen3.5-9B-MTP-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.5-9B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Qwen3.5-9B-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 unsloth/Qwen3.5-9B-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 unsloth/Qwen3.5-9B-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 unsloth/Qwen3.5-9B-MTP-GGUF to start chatting

How to use unsloth/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

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": "unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

Run Hermes

hermes

OpenClaw new

How to use unsloth/Qwen3.5-9B-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/Qwen3.5-9B-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/Qwen3.5-9B-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"

Docker Model Runner
How to use unsloth/Qwen3.5-9B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3.5-9B-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-9B-MTP-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

danielhanchen commited on May 16

Commit

9716a63

verified ·

1 Parent(s): c4bdf74

README: MTP merged 16 May 2026, update build cmd, remove ngram chain, n_max 2→6

Browse files

Files changed (1) hide show

README.md +7 -13

README.md CHANGED Viewed

@@ -30,16 +30,18 @@ tags:
     </a>
   </div>
     <ul style="margin: 0;">
-    <li><b>NEW: MTP speculative decoding for ~1.5-2x faster generation - build llama.cpp from the <a href="https://github.com/ggml-org/llama.cpp/pull/22673">MTP PR branch</a>:</b>
 > **Note:** llama.cpp [renamed](https://github.com/ggml-org/llama.cpp/pull/22673/commits/655c5773854dfd3deb2b6a1e66695d992ba83708) `--spec-type mtp` to `--spec-type draft-mtp` on 2026-05-13
 ```bash
 apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
-git clone -b mtp-clean https://github.com/am17an/llama.cpp.git
-cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
-cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-server
 cp llama.cpp/build/bin/llama-* llama.cpp
 ```
@@ -48,17 +50,9 @@ export LLAMA_CACHE="unsloth/Qwen3.5-9B-MTP-GGUF"
 ./llama.cpp/llama-server \
     -hf unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL \
     -ngl 99 -c 8192 -fa on -np 1 \
-    --spec-type draft-mtp --spec-draft-n-max 2
 ```
-For even faster generation, chain `ngram-mod` in front of MTP (parallel drafting from [PR #22838](https://github.com/ggml-org/llama.cpp/pull/22838)) - ngram catches verbatim repeats from the prompt while MTP drafts novel tokens:
-```bash
-./llama.cpp/llama-server \
-    -hf unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL \
-    -ngl 99 -c 8192 -fa on -np 1 \
-    --spec-type ngram-mod,draft-mtp --spec-draft-n-max 4
-```
 Set `-DGGML_CUDA=OFF` for CPU/Metal. `-np > 1` and `--mmproj` are not yet supported with MTP.
 </li>

     </a>
   </div>
     <ul style="margin: 0;">
+    <li><b>NEW: MTP speculative decoding for ~1.5-2x faster generation - build llama.cpp from the <a href="https://github.com/ggml-org/llama.cpp/pull/22673">MTP PR branch</a> - has been merged 16th May 2026!</b>
 > **Note:** llama.cpp [renamed](https://github.com/ggml-org/llama.cpp/pull/22673/commits/655c5773854dfd3deb2b6a1e66695d992ba83708) `--spec-type mtp` to `--spec-type draft-mtp` on 2026-05-13
 ```bash
+apt-get update
 apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
+git clone https://github.com/ggml-org/llama.cpp
+cmake llama.cpp -B llama.cpp/build \
+    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
+cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
 cp llama.cpp/build/bin/llama-* llama.cpp
 ```
 ./llama.cpp/llama-server \
     -hf unsloth/Qwen3.5-9B-MTP-GGUF:UD-Q4_K_XL \
     -ngl 99 -c 8192 -fa on -np 1 \
+    --spec-type draft-mtp --spec-draft-n-max 6
 ```
 Set `-DGGML_CUDA=OFF` for CPU/Metal. `-np > 1` and `--mmproj` are not yet supported with MTP.
 </li>