Instructions to use shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC with Transformers:

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

pipe = pipeline("image-text-to-text", model="shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC")
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("shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC")
model = AutoModelForMultimodalLM.from_pretrained("shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC")
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 shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC",
		"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/shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC

SGLang

How to use shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC 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 "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC" \
    --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": "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC",
		"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 "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC" \
        --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": "shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC",
		"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 shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC with Docker Model Runner:
```
docker model run hf.co/shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC
```

Model quant requests?

by pathosethoslogos - opened Apr 21

Discussion

pathosethoslogos

Apr 21

Been loving this model!

Just out of curiosity, do you take requests? It would be amazing if same quant approach was applied to the new Qwen3.6. 😊

shieldstar

Owner Apr 21

On it, had it on my mind a few hours ago

ak-dome

May 17

Could I please ask you to create a high-quality quantization for the Qwen3.5-397B-A17B model?
Intel's current version fits into a dual-Spark setup with full context, but it uses uncalibrated RTN quantization.
As a result, it sometimes performs worse than the 122B model.

https://huggingface.co/Intel/Qwen3.5-397B-A17B-int4-AutoRound
"The model is quantized via RTN mode"

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