QwQ 32B

Alibaba

qwen

Reasoning model from the Qwen family, rivaling DeepSeek R1 on benchmarks.

Model info

Model

QwQ 32B

Author

Alibaba

Arch

qwen

Parameters

32B

Format

gguf

Size on disk

about 19.85 GB

Download and run QwQ 32B

Open in LM Studio to view download options

Download qwq-32b from the terminal

Download the model using lms — LM Studio's developer CLI.

lms get qwq-32b

Call qwq-32b from your code

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwq-32b",
    "messages": [
      { "role": "system", "content": "Always answer in rhymes." },
      { "role": "user", "content": "Introduce yourself." }
    ],
    "temperature": 0.7,
    "max_tokens": -1,
    "stream": true
  }'

Next Steps: Build! 🔨

Learn more