nuckcrews/Qwen3-0.6B-pub

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 1, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3-0.6B-pub is a 0.6 billion parameter causal language model from the Qwen3 series, developed by Qwen. This model uniquely supports seamless switching between a 'thinking mode' for complex logical reasoning, math, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It features enhanced reasoning capabilities, superior human preference alignment for creative writing and role-playing, and strong agent capabilities, supporting over 100 languages with a 32,768 token context length.

Loading preview...

Qwen3-0.6B Overview

Qwen3-0.6B is a 0.6 billion parameter causal language model from the Qwen series, designed for advanced reasoning and versatile conversational applications. It introduces a novel capability to seamlessly switch between a 'thinking mode' for complex tasks like logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This dual-mode functionality ensures optimal performance across diverse scenarios.

Key Capabilities

  • Dynamic Thinking Modes: Uniquely supports a hard or soft switch between a detailed reasoning mode (for complex problem-solving) and an efficient, direct response mode (for general dialogue).
  • Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning, surpassing previous Qwen models.
  • Superior Human Preference Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, providing a more natural and engaging user experience.
  • Advanced Agent Capabilities: Offers robust integration with external tools, achieving leading performance in complex agent-based tasks among open-source models.
  • Multilingual Support: Capable of handling over 100 languages and dialects, with strong multilingual instruction following and translation abilities.
  • Extended Context Length: Features a substantial context window of 32,768 tokens.

Best Practices for Usage

To optimize performance, specific sampling parameters are recommended for each mode:

  • Thinking Mode (enable_thinking=True): Use Temperature=0.6, TopP=0.95, TopK=20, and MinP=0. Greedy decoding is not recommended.
  • Non-Thinking Mode (enable_thinking=False): Suggested parameters are Temperature=0.7, TopP=0.8, TopK=20, and MinP=0.

Additionally, using an adequate output length (e.g., 32,768 tokens) and standardizing output formats with specific prompts for math or multiple-choice questions can further enhance results. The model also supports agentic use with tools like Qwen-Agent for streamlined tool-calling.

Finetunes
1 models