sparkling1118/Qwen3-1.7B

TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Qwen3-1.7B is a 1.7 billion parameter causal language model developed by Qwen, featuring a unique ability to seamlessly switch between 'thinking' and 'non-thinking' modes for optimized performance. This model excels in complex logical reasoning, mathematics, code generation, and agent capabilities, while also supporting over 100 languages. It is designed for enhanced instruction-following, creative writing, and multi-turn dialogues, offering a comprehensive solution for diverse AI applications.

Loading preview...

Qwen3-1.7B Model Overview

Qwen3-1.7B is a 1.7 billion parameter causal language model from the Qwen series, distinguished by its innovative dual-mode operation. It can dynamically switch between a 'thinking mode' for complex logical reasoning, mathematics, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. This flexibility allows for optimal performance across a wide range of tasks.

Key Capabilities and Features

  • Dynamic Thinking Modes: Seamlessly transitions between a reasoning-focused mode and a general dialogue mode, enhancing performance in both complex and routine interactions.
  • Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning, surpassing previous Qwen models.
  • Superior Human Alignment: Excels in creative writing, role-playing, and multi-turn conversations, providing a more natural and engaging user experience.
  • Advanced Agent Capabilities: Offers robust integration with external tools, achieving leading performance among open-source models in complex agent-based tasks.
  • Multilingual Support: Supports over 100 languages and dialects, with strong capabilities for multilingual instruction following and translation.
  • Context Length: Features a substantial context length of 32,768 tokens.

Good For

  • Applications requiring advanced logical reasoning and problem-solving.
  • Code generation and mathematical tasks.
  • Creative writing, role-playing, and engaging multi-turn dialogues.
  • Developing AI agents that interact with external tools.
  • Multilingual applications needing strong instruction following and translation.

Finetunes
1 models