Math and reasoning · Alibaba Qwen

QwQ 32B

Hugging Face: Qwen/QwQ-32B · checked 2026-10-13

Qwen's first open reasoning model; still a strong all-rounder on a 24 GB card.

Datasheet

Maker	Alibaba Qwen
Parameters	32.76 BVerifiedsafetensors.total from the HF API Source
Licence	Apache-2.0Verified
Access	Public download
Task (HF pipeline)	text-generation
First published on HF	2025-03-05
Last updated on HF	2025-03-11
Weights in memory	66 GB at 16-bit · 20 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

79.5%

AIME 2024, pass@1 · #3 of 7 scored in this category

Third-party report: the QwQ 32B row in Microsoft's Phi-4-reasoning model card. Source

Other published results

LMArena text, math category: 1,358.9Sourced Source

See the full math and reasoning ranking

The description summarises the model card at https://huggingface.co/Qwen/QwQ-32B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.