Instructions to use drawais/QwQ-32B-AWQ-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drawais/QwQ-32B-AWQ-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="drawais/QwQ-32B-AWQ-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drawais/QwQ-32B-AWQ-INT4")
model = AutoModelForCausalLM.from_pretrained("drawais/QwQ-32B-AWQ-INT4")
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

vLLM

How to use drawais/QwQ-32B-AWQ-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drawais/QwQ-32B-AWQ-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drawais/QwQ-32B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/drawais/QwQ-32B-AWQ-INT4

SGLang

How to use drawais/QwQ-32B-AWQ-INT4 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 "drawais/QwQ-32B-AWQ-INT4" \
    --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": "drawais/QwQ-32B-AWQ-INT4",
		"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 "drawais/QwQ-32B-AWQ-INT4" \
        --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": "drawais/QwQ-32B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use drawais/QwQ-32B-AWQ-INT4 with Docker Model Runner:
```
docker model run hf.co/drawais/QwQ-32B-AWQ-INT4
```

QwQ-32B-AWQ-INT4

INT4 weight-only quantization of Qwen/QwQ-32B.

Alibaba QwQ-32B reasoning model in INT4. About 17 GB on disk. Runs on a single 24 GB consumer GPU.

Property	Value
Base model	Qwen/QwQ-32B
Quantization	INT4 weight-only
Approx. on-disk size	~19.2 GB
License	Apache License, Version 2.0
Languages	English

Load (vLLM)

vllm serve drawais/QwQ-32B-AWQ-INT4 \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.94

from vllm import LLM, SamplingParams
llm = LLM(model="drawais/QwQ-32B-AWQ-INT4", max_model_len=32768)
print(llm.generate(["Hello!"], SamplingParams(max_tokens=128))[0].outputs[0].text)

Footprint

~19.2 GB on disk. Recommended VRAM: enough headroom for KV cache.

License & attribution

This artifact is a derivative work of Qwen/QwQ-32B, released by its original authors under the Apache License, Version 2.0.

This artifact is distributed under the same license. The full license text is included in LICENSE, and required attribution is in NOTICE.

License text: https://www.apache.org/licenses/LICENSE-2.0 Source model: https://huggingface.co/Qwen/QwQ-32B

Downloads last month: 14

Safetensors

Model size

33B params

Tensor type

I64

I32

BF16

Model tree for drawais/QwQ-32B-AWQ-INT4

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Quantized

(163)

this model