Instructions to use Dracones/QwQ-32B_exl2_4.5bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dracones/QwQ-32B_exl2_4.5bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dracones/QwQ-32B_exl2_4.5bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Dracones/QwQ-32B_exl2_4.5bpw")
model = AutoModelForMultimodalLM.from_pretrained("Dracones/QwQ-32B_exl2_4.5bpw")
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 Dracones/QwQ-32B_exl2_4.5bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dracones/QwQ-32B_exl2_4.5bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dracones/QwQ-32B_exl2_4.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dracones/QwQ-32B_exl2_4.5bpw

SGLang

How to use Dracones/QwQ-32B_exl2_4.5bpw 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 "Dracones/QwQ-32B_exl2_4.5bpw" \
    --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": "Dracones/QwQ-32B_exl2_4.5bpw",
		"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 "Dracones/QwQ-32B_exl2_4.5bpw" \
        --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": "Dracones/QwQ-32B_exl2_4.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dracones/QwQ-32B_exl2_4.5bpw with Docker Model Runner:
```
docker model run hf.co/Dracones/QwQ-32B_exl2_4.5bpw
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

QwQ-32B - EXL2 4.5bpw

This is a 4.5bpw EXL2 quant of Qwen/QwQ-32B

Details about the model can be found at the above model page.

Perplexity Scoring

Below are the perplexity scores for the EXL2 models. A lower score is better.

Quant Level	Perplexity Score
8.0	6.4393
7.0	6.4452
6.0	6.4693
5.0	6.4732
4.5	6.5417
4.0	6.6190

Downloads last month: 5

Model tree for Dracones/QwQ-32B_exl2_4.5bpw

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Quantized

(163)

this model