unsloth/Qwen3-1.7B

Qwen3-1.7B: Adaptable Intelligence with Thinking Modes

Qwen3-1.7B is a 1.7 billion parameter causal language model from the Qwen series, developed by the Qwen Team. It introduces a novel feature allowing seamless switching between two distinct operational modes:

Key Capabilities

• Thinking Mode: Engages advanced reasoning for complex logical tasks, mathematics, and code generation, significantly enhancing performance in these areas.
• Non-Thinking Mode: Optimized for efficient, general-purpose dialogue and instruction following, aligning with the functionality of previous Qwen2.5-Instruct models.
• Superior Human Preference Alignment: Excels in creative writing, role-playing, and multi-turn conversations, delivering engaging and natural interactions.
• Advanced Agent Capabilities: Integrates precisely with external tools, achieving leading performance in complex agent-based tasks among open-source models.
• Multilingual Support: Supports over 100 languages and dialects with strong capabilities for multilingual instruction following and translation.

Good For

• Applications requiring dynamic switching between analytical reasoning and conversational efficiency.
• Complex problem-solving in mathematics and coding.
• Creative content generation and interactive role-playing scenarios.
• Developing sophisticated AI agents with tool-use capabilities.
• Multilingual applications needing robust instruction following and translation.