Qwen Releases Updated Qwen3-30B-A3B-Instruct-2507 Non-Thinking Mode Model
By
tosh
10mo ago· 9 min readen
100/100
Golden Brown
Bagelometer↗
Crisp on the outside, thoughtful on the inside. A keeper.
Score100Typepress releaseSentimentpositive
Summary
Qwen (Alibaba's AI team) released an updated version of their Qwen3-30B-A3B model, named Qwen3-30B-A3B-Instruct-2507. This is a non-thinking mode model (no <think> blocks in output) with key enhancements over the previous version. The model is part of their open-source AI initiative, and the announcement directs users to their blog, GitHub, and documentation for benchmarks, hardware requirements, and inference performance details.
Key quotes
· 3 pulledWe introduce the updated version of the Qwen3-30B-A3B non-thinking mode, named Qwen3-30B-A3B-Instruct-2507
This model supports only non-thinking mode and does not generate <think></think> blocks in its output.
We're on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
