Instructions to use empero-ai/Qwen3.8-9B-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use empero-ai/Qwen3.8-9B-Distill with Transformers:

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

pipe = pipeline("text-generation", model="empero-ai/Qwen3.8-9B-Distill")
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("empero-ai/Qwen3.8-9B-Distill")
model = AutoModelForMultimodalLM.from_pretrained("empero-ai/Qwen3.8-9B-Distill", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use empero-ai/Qwen3.8-9B-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "empero-ai/Qwen3.8-9B-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "empero-ai/Qwen3.8-9B-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/empero-ai/Qwen3.8-9B-Distill

SGLang

How to use empero-ai/Qwen3.8-9B-Distill 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 "empero-ai/Qwen3.8-9B-Distill" \
    --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": "empero-ai/Qwen3.8-9B-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "empero-ai/Qwen3.8-9B-Distill" \
        --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": "empero-ai/Qwen3.8-9B-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use empero-ai/Qwen3.8-9B-Distill with Docker Model Runner:
```
docker model run hf.co/empero-ai/Qwen3.8-9B-Distill
```

URGENT: Update the Title to Include Unofficial or Distilled

by Abdelhak - opened 4 days ago

Discussion

Abdelhak

4 days ago

The title is super misleading and confusing. This is NOT Qwen3.8-9B and it's not an official released either.

grumd0

4 days ago

Agreed. Please rename the model. This is a very bad look. The model name is incredibly deceiving and disingenuous.

TomLucidor

4 days ago

It's a fun prank, anyone who don't check the sources would be The Onion'd by this. Maybe this can bait the real makers of Qwen3.8 to reconsider and make smaller models accessible

popeyed

4 days ago

It's a fun prank, anyone who don't check the sources would be The Onion'd by this. Maybe this can bait the real makers of Qwen3.8 to reconsider and make smaller models accessible

Or it might have the opposite effect. Since now they might think it's already done by someone else and they don't have to do it themselves.

TomLucidor

3 days ago

They can always check, by standard convention it is not who "name it first" but who is "legit" so pranksters might spark something in them

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