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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="havenoammo/Qwen3.6-27B-MTP-UD-GGUF")

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "havenoammo/Qwen3.6-27B-MTP-UD-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "havenoammo/Qwen3.6-27B-MTP-UD-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/havenoammo/Qwen3.6-27B-MTP-UD-GGUF

SGLang

How to use havenoammo/Qwen3.6-27B-MTP-UD-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 "havenoammo/Qwen3.6-27B-MTP-UD-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "havenoammo/Qwen3.6-27B-MTP-UD-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "havenoammo/Qwen3.6-27B-MTP-UD-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "havenoammo/Qwen3.6-27B-MTP-UD-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use havenoammo/Qwen3.6-27B-MTP-UD-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 havenoammo/Qwen3.6-27B-MTP-UD-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 havenoammo/Qwen3.6-27B-MTP-UD-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="havenoammo/Qwen3.6-27B-MTP-UD-GGUF",
    max_seq_length=2048,
)

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

add Q3 please

by Y4iges - opened May 7

Discussion

Y4iges

May 7

•

edited May 7

add Q3 please, for users with 16 vram.

Y4iges changed discussion status to closed May 7

havenoammo

Owner May 7

Sure, will do!

havenoammo

Owner May 7

•

edited May 7

Added Q2 and Q3, though depending on your settings they can sometimes output gibberish. Not sure if it's a bug in the MTP implementation or in llama.cpp itself, since the base model without MTP also showed the same issue occasionally.

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