Intel / article

Qwen3: Think Deeper, Act Faster

Source: Qwen Team
Author: Qwen Team
Date: Published Apr 28, 2025

Terms in this piece · Glossary

mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.

Why it matters

Qwen3 introduces hybrid reasoning (switchable thinking/non-thinking modes) and models where a 30B-A3B activates only 3B parameters yet outperforms much larger models, giving builders strong, self-hostable alternatives to closed frontier APIs.

Key quotes

“Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tier models such as DeepSeek-R1, o1, o3-mini, Grok-3, and Gemini-2.5-Pro.”

“Additionally, the small MoE model, Qwen3-30B-A3B, outcompetes QwQ-32B with 10 times of activated parameters, and even a tiny model like Qwen3-4B can rival the performance of Qwen2.”

Read the source ↗qwenlm.github.io