Instructions to use Qwen/QwQ-32B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use Qwen/QwQ-32B-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/QwQ-32B-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": "Qwen/QwQ-32B-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Qwen/QwQ-32B-AWQ
- SGLang
How to use Qwen/QwQ-32B-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 "Qwen/QwQ-32B-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": "Qwen/QwQ-32B-AWQ", "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 "Qwen/QwQ-32B-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": "Qwen/QwQ-32B-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Qwen/QwQ-32B-AWQ with Docker Model Runner:
docker model run hf.co/Qwen/QwQ-32B-AWQ
GPTQ quants
#5
by dazipe - opened
Hello,
Would you consider uploading GPTQ 4bit and 8bit quants for the Qwen/QwQ-32B?
The AWQ is supported on newer GPUs only. Support is particularly poor on AMD cards.
You have provided it previously. For example your GPTQ quants have the most downloads for the Qwen2.5-32B-Instruct:
https://huggingface.co/models?other=base_model:quantized:Qwen%2FQwen2.5-32B-Instruct&sort=downloads