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

Libraries

How to use QuantTrio/Qwen3.6-35B-A3B-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="QuantTrio/Qwen3.6-35B-A3B-AWQ")
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("QuantTrio/Qwen3.6-35B-A3B-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("QuantTrio/Qwen3.6-35B-A3B-AWQ", 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 QuantTrio/Qwen3.6-35B-A3B-AWQ with vLLM:

Install from pip and serve model

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

SGLang

How to use QuantTrio/Qwen3.6-35B-A3B-AWQ 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 "QuantTrio/Qwen3.6-35B-A3B-AWQ" \
    --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": "QuantTrio/Qwen3.6-35B-A3B-AWQ",
		"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 "QuantTrio/Qwen3.6-35B-A3B-AWQ" \
        --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": "QuantTrio/Qwen3.6-35B-A3B-AWQ",
		"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 QuantTrio/Qwen3.6-35B-A3B-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/Qwen3.6-35B-A3B-AWQ
```

AWQ - 8 Bit

by shrisha - opened Apr 17

Discussion

shrisha

Apr 17

Hello, Just wondering, are you planing do the 8 Bit model as well?
Thanks.
Greetings!

Apr 23

这个需求现在开始变得强烈而合理。
https://github.com/vllm-project/vllm/issues/39749
vllm 第二季度的核心目标之一是实现权重从 vram 卸载到 dram 或磁盘。
然后这些工作这几天陆续已经合并了，在 vllm0.20 就可以用得上了
https://github.com/vllm-project/vllm/issues/38256

如果是特定用例，MoE的权重激活一般在 12%-30%. Qwen3.5 系列专家数量在 128，稀疏度相对高，这是权重卸载非常适用的模型。而这个模型是地球上最经典的适配 rtx3090 的模型。

我和 Gemini Pro, Claude 讨论，权重卸载的情况下，要同时能在 RTX3090 上单卡运行，速度极快，精度极高，上下文充足，最佳的格式会是什么。都告诉我是 awq8bit 外加 bfloat16 激活。

所以，如果 awq-8bit 发布，那么在过几天 vllm0.20 发布后，刚好赶得上第一波最经典，强烈的需求。

我对你们的模型非常有好感。微调普遍会损坏模型，量化也难免损失很大，你们的模型是地球上量化最出色的。如果问 8bit awq 最经典的版本是谁家的？我感觉理应是你们制作的。

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