Instructions to use havenoammo/Qwen3.6-35B-A3B-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use havenoammo/Qwen3.6-35B-A3B-MTP-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="havenoammo/Qwen3.6-35B-A3B-MTP-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("havenoammo/Qwen3.6-35B-A3B-MTP-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use havenoammo/Qwen3.6-35B-A3B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "havenoammo/Qwen3.6-35B-A3B-MTP-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/Qwen3.6-35B-A3B-MTP-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF

SGLang

How to use havenoammo/Qwen3.6-35B-A3B-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 "havenoammo/Qwen3.6-35B-A3B-MTP-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/Qwen3.6-35B-A3B-MTP-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/Qwen3.6-35B-A3B-MTP-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/Qwen3.6-35B-A3B-MTP-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use havenoammo/Qwen3.6-35B-A3B-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 havenoammo/Qwen3.6-35B-A3B-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 havenoammo/Qwen3.6-35B-A3B-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 havenoammo/Qwen3.6-35B-A3B-MTP-GGUF to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="havenoammo/Qwen3.6-35B-A3B-MTP-GGUF",
    max_seq_length=2048,
)

Docker Model Runner
How to use havenoammo/Qwen3.6-35B-A3B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF
```

Is it possible to only download the mtp gguf (<1GB one) to use with existing ggufs?

by CHNtentes - opened 27 days ago

Discussion

CHNtentes

27 days ago

Or do I need to download the whole new gguf with mtp inside

havenoammo

Owner 27 days ago

Sure! You can download just the MTP gguf from https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF/resolve/main/35BA3B-MTP.gguf and the convert.py script from https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF/resolve/main/convert.py, then graft the MTP layers onto your existing model by following this recipe:

# Create and activate a virtual environment
uv venv .venv --seed
source .venv/bin/activate

# Install the gguf library
uv pip install gguf

# Run the grafting script: convert.py <base model> <MTP source> <output>
python convert.py Qwen3.6-27B-UD-Q4_K_XL.gguf MTP-Q8_0.gguf Qwen3.6-27B-MTP-UD-Q4_K_XL.gguf

CHNtentes

27 days ago

Sure! You can download just the MTP gguf from https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF/resolve/main/35BA3B-MTP.gguf and the convert.py script from https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF/resolve/main/convert.py, then graft the MTP layers onto your existing model by following this recipe:
# Create and activate a virtual environment
uv venv .venv --seed
source .venv/bin/activate

# Install the gguf library
uv pip install gguf

# Run the grafting script: convert.py <base model> <MTP source> <output>
python convert.py Qwen3.6-27B-UD-Q4_K_XL.gguf MTP-Q8_0.gguf Qwen3.6-27B-MTP-UD-Q4_K_XL.gguf

Thanks!

mayankiit04

25 days ago

So if i have a IQ4_NL from UD, i can still patch it with MTP-Q8_0.gguf??

havenoammo

Owner 25 days ago

So if i have a IQ4_NL from UD, i can still patch it with MTP-Q8_0.gguf??

Yes, that's right.

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