Instructions to use Lorbus/Qwen3.6-27B-int4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lorbus/Qwen3.6-27B-int4-AutoRound with Transformers:

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

pipe = pipeline("image-text-to-text", model="Lorbus/Qwen3.6-27B-int4-AutoRound")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Lorbus/Qwen3.6-27B-int4-AutoRound")
model = AutoModelForImageTextToText.from_pretrained("Lorbus/Qwen3.6-27B-int4-AutoRound")
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

vLLM

How to use Lorbus/Qwen3.6-27B-int4-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lorbus/Qwen3.6-27B-int4-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lorbus/Qwen3.6-27B-int4-AutoRound",
		"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/Lorbus/Qwen3.6-27B-int4-AutoRound

SGLang

How to use Lorbus/Qwen3.6-27B-int4-AutoRound 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 "Lorbus/Qwen3.6-27B-int4-AutoRound" \
    --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": "Lorbus/Qwen3.6-27B-int4-AutoRound",
		"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 "Lorbus/Qwen3.6-27B-int4-AutoRound" \
        --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": "Lorbus/Qwen3.6-27B-int4-AutoRound",
		"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 Lorbus/Qwen3.6-27B-int4-AutoRound with Docker Model Runner:
```
docker model run hf.co/Lorbus/Qwen3.6-27B-int4-AutoRound
```

How does this fair against other quants without MTP like unsloth?

by Crigges - opened 13 days ago

Discussion

Crigges

13 days ago

How well does Intel Autoround in comparison to unsloth's or bartowski's Q4? Don't get me wrong MTP is great, but what does it cost in quality?

ubergarm

2 days ago

Its a good question and it is challenging to compare across vLLM and llama ecosystem.

A few data points where I did a 3 way benchmark between vLLM (not patched with Genesis/turboquant stuff), ik_llama.cpp, and mainline llama.cpp for speed only:

https://github.com/noonghunna/club-3090/pull/64#issuecomment-4383699676

In terms of quality, I have an ik_llama.cpp exclusive quant that runs well on a single 3090 in 24GB VRAM including full q8_0 quality MTP tensors here:

https://huggingface.co/ubergarm/Qwen3.6-27B-GGUF/discussions/2#69fa0f7d8ab0c1b3e49d8e58

You can see my recipes are very competitive looking at oobabooga's comparisons (his substack and methods give good data): https://huggingface.co/ubergarm/Qwen3.6-27B-GGUF/discussions/1#69f1434b22f130c604d3a2bf

So you can have MTP with GGUFs now too!

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