Yahel666/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 8, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

Yahel666/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 enhances capabilities in coding, mathematics, and instruction following, supporting a 32,768 token context length. It excels at generating long texts, understanding structured data like JSON, and offers robust multilingual support across 29 languages. Optimized for diverse chatbot implementations and structured output generation, it provides improved resilience to varied system prompts.

Loading preview...

Qwen2.5-3B-Instruct Overview

Yahel666/Qwen2.5-3B-Instruct is an instruction-tuned model from the latest Qwen2.5 series, featuring 3.09 billion parameters and a 32,768 token context length. Developed by Qwen, this model builds upon the Qwen2 architecture with significant enhancements across several key areas.

Key Capabilities

  • Enhanced Knowledge & Reasoning: Demonstrates greatly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Offers significant improvements in adhering to instructions and generating long texts (up to 8K tokens).
  • Structured Data Handling: Excels at understanding structured data, such as tables, and generating structured outputs, particularly JSON.
  • Robust Chatbot Implementation: More resilient to diverse system prompts, enhancing role-play and condition-setting for chatbots.
  • Multilingual Support: Provides comprehensive support for over 29 languages, including major global languages like Chinese, English, French, Spanish, and Japanese.

What Makes It Different

This model stands out due to its focused improvements in technical domains like coding and math, combined with advanced instruction following and structured output generation. Its ability to handle long contexts and generate extensive responses, alongside strong multilingual support, makes it a versatile choice for applications requiring precise control and diverse language capabilities. The underlying architecture includes transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings.

Finetunes
1 models