hoangquan456/
qwen3-nothink

1,176 2 months ago

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. This version of Qwen3 is optimized for direct, concise responses without thinking.

tools 0.6b 1.7b 4b 8b 14b

Models

View all →

5 models

qwen3-nothink:0.6b

523MB · 40K context window · Text · 2 months ago

qwen3-nothink:1.7b

1.4GB · 40K context window · Text · 2 months ago

qwen3-nothink:4b

2.6GB · 40K context window · Text · 2 months ago

qwen3-nothink:8b

5.2GB · 40K context window · Text · 2 months ago

qwen3-nothink:14b

9.3GB · 40K context window · Text · 2 months ago

Readme

Qwen3-NoThink

Features

  • Optimized for speed: No thinking, instant responses.
  • IDE-ready: Works with Continue.dev, Copilot, and Cline.
  • Code-first: Prioritizes direct answers over explanations.

Usage

ollama pull hoangquan456/qwen3-nothink