QwQ-32B is a 32-billion-parameter large language model from the Qwen team, released on Hugging Face. It is designed for advanced reasoning, mathematical problem solving, and tool/function calling tasks. The model weights are fully open, allowing developers to run it locally, via Docker, or through self-hosted inference endpoints using standard Hugging Face tools.
QwQ 32B is a Foundation models & chat product. It focuses on accessing and running a high-performance open-weight reasoning model locally or via self-hosted inference without relying on proprietary APIs. It is built as an open-source project for developers. QwQ 32B is open source under the Open Source license. QwQ 32B is available on the web, the command line, and API, and it can be self-hosted.
Behind QwQ 32B is Qwen, and the product first shipped in 2024. Development happens publicly on GitHub with 27.4k stars. It operates in a well-populated space: PulseGate tracks 6 similar tools. Key capabilities include Tool Calling, reasoning, and Function Calling. It exposes integrations via a public API.
Latest indexed changes and source events
Other apps tracked under the same category.
