Instructions to use ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ")
model = AutoModelForMultimodalLM.from_pretrained("ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ",
		"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/ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ

SGLang

How to use ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ 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 "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ" \
    --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": "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ",
		"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 "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ" \
        --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": "ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ
```

gguf please?

by Splarkszter - opened 11 days ago

Discussion

Splarkszter

11 days ago

I'd love to see one of your GSQ-RCO GGUF for Qwen3.6 35b-a3b.
We won't be getting an MoE this good and this small for a while.
I doubt Qwen4 is less on than 2months. So please :)

pieris98

3 days ago

As much as I would love a gguf myself, I believe it's a challenge to make this specific 2-bit-GSQ Humming quant work in llama.cpp or convert into a gguf.
The Humming format is custom and the quant is also non-standard. They would need to port the Triton vLLM kernels and patch to CUDA C kernels and custom C/C++ types, code and patches for a ggml/llama.cpp branch supporting this 2-Bit GSQ quant.
Perhaps a better ask for the lab (please do) is IQ3_XS/IQ3_S/IQ3_M GSQ-RCO quants for MoE Qwen3.6-35B-A3B, similar to the lab's quants of the Qwen3.8-Flash-27B dense model.

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