Instructions to use Dundell391/Qwen3-32B_exl2_6.0bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dundell391/Qwen3-32B_exl2_6.0bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dundell391/Qwen3-32B_exl2_6.0bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dundell391/Qwen3-32B_exl2_6.0bpw")
model = AutoModelForCausalLM.from_pretrained("Dundell391/Qwen3-32B_exl2_6.0bpw", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dundell391/Qwen3-32B_exl2_6.0bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dundell391/Qwen3-32B_exl2_6.0bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dundell391/Qwen3-32B_exl2_6.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dundell391/Qwen3-32B_exl2_6.0bpw

SGLang

How to use Dundell391/Qwen3-32B_exl2_6.0bpw 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 "Dundell391/Qwen3-32B_exl2_6.0bpw" \
    --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": "Dundell391/Qwen3-32B_exl2_6.0bpw",
		"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 "Dundell391/Qwen3-32B_exl2_6.0bpw" \
        --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": "Dundell391/Qwen3-32B_exl2_6.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dundell391/Qwen3-32B_exl2_6.0bpw with Docker Model Runner:
```
docker model run hf.co/Dundell391/Qwen3-32B_exl2_6.0bpw
```

Problem with exllamav2

by tatianapoliakova - opened May 4, 2025

Discussion

tatianapoliakova

May 4, 2025

•

edited May 6, 2025

The latest exllamav2 and flash attention were installed. I use RTX 3xxx. I get gibberish, other models like qwen 2.5 work great. It seems that exllamav2 doesn't support the latest models yet.

hellofans

May 8, 2025

you need to use the DEV branch of exllamav2 as there is no support on the main branch

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