zsansan/Qwen2.5-3B-Instruct

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 11, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

Qwen2.5-3B-Instruct is a 3.09 billion parameter instruction-tuned causal language model from the Qwen2.5 series, developed by Qwen. It features a transformer architecture with RoPE, SwiGLU, and RMSNorm, supporting a 32,768 token context length. This model significantly enhances capabilities in coding, mathematics, instruction following, and generating structured outputs like JSON, making it suitable for diverse applications requiring robust language understanding and generation.

Loading preview...

Qwen2.5-3B-Instruct: Enhanced Language Model

Qwen2.5-3B-Instruct is an instruction-tuned causal language model from the Qwen2.5 series, featuring 3.09 billion parameters and a 32,768 token context length. Developed by Qwen, this model builds upon its predecessors with significant improvements across several key areas.

Key Capabilities & Enhancements

  • Expanded Knowledge & Specialized Skills: Demonstrates greatly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following & Output Generation: Offers significant advancements in instruction following, generating long texts (up to 8K tokens), and understanding/generating structured data, particularly JSON outputs. It is also more resilient to diverse system prompts, enhancing role-play and chatbot condition-setting.
  • Long-Context Support: Supports a full context length of 32,768 tokens and can generate up to 8,192 tokens.
  • Multilingual Support: Provides robust support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.

Architecture & Training

This model utilizes a transformer architecture incorporating RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings. It was developed through both pretraining and post-training stages.

Ideal Use Cases

This model is well-suited for applications requiring:

  • Accurate code generation and mathematical problem-solving.
  • Reliable instruction following and complex task execution.
  • Generation of structured data formats like JSON.
  • Long-form content generation and summarization.
  • Multilingual conversational AI and content creation.

Finetunes
1 models