liuw15/qwen3-8b-ziyon-nsfw

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The liuw15/qwen3-8b-ziyon-nsfw model is an 8.2 billion parameter causal language model from the Qwen3 series, developed by Qwen. It uniquely supports seamless switching between a 'thinking mode' for complex reasoning, math, and coding, and a 'non-thinking mode' for general dialogue, with a native context length of 32,768 tokens. This model excels in reasoning capabilities, human preference alignment for creative writing and role-playing, and agentic tasks, making it versatile for diverse AI applications.

Loading preview...

Qwen3-8B Overview

Qwen3-8B is an 8.2 billion parameter causal language model from the Qwen series, designed for advanced reasoning and flexible application. It features a unique capability to switch between a 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This dual-mode functionality ensures optimal performance across various scenarios, enhancing both accuracy and efficiency.

Key Capabilities

  • Adaptive Reasoning: Seamlessly transitions between modes to handle tasks requiring deep thought (e.g., math, coding) and those needing quick, general responses.
  • Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning compared to previous Qwen models.
  • Human Preference Alignment: Excels in creative writing, role-playing, and multi-turn conversations, providing a more natural and engaging user experience.
  • Agentic Expertise: Offers strong tool-calling capabilities, integrating precisely with external tools in both thinking and unthinking modes, achieving leading performance in complex agent-based tasks.
  • Multilingual Support: Supports over 100 languages and dialects, with robust capabilities for multilingual instruction following and translation.
  • Extended Context: Natively handles a context length of 32,768 tokens, extendable up to 131,072 tokens using the YaRN method for processing long texts.

Good for

  • Applications requiring dynamic reasoning capabilities.
  • Creative content generation and interactive role-playing scenarios.
  • Complex agent-based systems and tool integration.
  • Multilingual applications and translation tasks.
  • Scenarios demanding long context understanding and generation.

Finetunes
2 models