ErtasAI/Qwen2.5-3B-Instruct

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 19, 2026License:qwen-researchArchitecture:Transformer Featherless Exclusive Cold

ErtasAI/Qwen2.5-3B-Instruct is a 3.09 billion parameter instruction-tuned causal language model from the Qwen2.5 series, developed by Qwen. This model significantly improves upon Qwen2 with enhanced knowledge, coding, and mathematics capabilities, alongside better instruction following and long text generation. It supports a 32,768 token context length and generates up to 8,192 tokens, making it suitable for complex tasks requiring extensive context and structured outputs like JSON. The model also offers robust multilingual support across over 29 languages.

Loading preview...

Overview

ErtasAI/Qwen2.5-3B-Instruct is an instruction-tuned model from the Qwen2.5 series, developed by Qwen. This 3.09 billion parameter causal language model builds upon the Qwen2 architecture, featuring transformers with RoPE, SwiGLU, and RMSNorm. It boasts a substantial context length of 32,768 tokens and can generate responses up to 8,192 tokens, making it well-suited for detailed and extensive interactions.

Key Capabilities

  • Enhanced Knowledge & Reasoning: Significantly improved capabilities in general knowledge, coding, and mathematics, leveraging specialized expert models.
  • Instruction Following: Demonstrates substantial improvements in adhering to instructions and generating structured outputs, including JSON.
  • Long-Context & Generation: Supports processing up to 128K tokens and generating up to 8K tokens, ideal for complex, multi-turn conversations or document analysis.
  • Multilingual Support: Offers robust support for over 29 languages, including major global languages like Chinese, English, French, Spanish, and more.
  • System Prompt Resilience: More resilient to diverse system prompts, enhancing its adaptability for role-play and conditional chatbot implementations.

Good For

  • Applications requiring strong coding and mathematical reasoning.
  • Chatbots and agents needing precise instruction following and structured output generation.
  • Tasks involving long text generation or analysis of extensive contexts.
  • Multilingual applications demanding broad language support.

Finetunes
2 models