Zidane29/Qwen3-0.6B

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3-0.6B is a 0.6 billion parameter causal language model developed by Qwen, featuring a 32,768 token context length. 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 demonstrates enhanced reasoning capabilities, superior human preference alignment for creative writing and multi-turn dialogues, and strong agent capabilities for tool integration.

Loading preview...

Overview

Qwen3-0.6B is a 0.6 billion parameter causal language model from the Qwen series, designed with a 32,768 token context length. It is distinguished by its innovative ability to switch between a 'thinking mode' for intricate tasks like logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for more straightforward, general-purpose conversational interactions. This dual-mode functionality aims to optimize performance across diverse scenarios.

Key Capabilities

  • Adaptive Thinking Modes: Seamlessly transitions between a reasoning-focused mode and an efficient dialogue mode within a single model instance.
  • Enhanced Reasoning: Shows significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning.
  • Human Preference Alignment: Excels in creative writing, role-playing, and multi-turn dialogues, providing a more natural and engaging user experience.
  • Agentic Functionality: Demonstrates strong capabilities for integrating with external tools, achieving leading performance in complex agent-based tasks among open-source models.
  • Multilingual Support: Supports over 100 languages and dialects, with robust multilingual instruction following and translation abilities.

Usage and Best Practices

Developers can enable or disable the thinking mode using the enable_thinking parameter in the tokenizer, or dynamically switch modes within conversations using /think and /no_think tags. The model also supports deployment via sglang and vllm for OpenAI-compatible API endpoints. Optimal sampling parameters are recommended for each mode to prevent performance degradation and repetitions, such as Temperature=0.6 for thinking mode and Temperature=0.7 for non-thinking mode. For agentic use, Qwen-Agent is recommended for simplified tool integration.