Itchymaroo/Qwen2.5-1.5B-Instruct

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Itchymaroo/Qwen2.5-1.5B-Instruct is a 1.54 billion parameter instruction-tuned causal language model from the Qwen2.5 series, developed by Qwen. It features a 32,768 token context length and is significantly improved in coding, mathematics, instruction following, and generating structured outputs like JSON. This model is optimized for diverse chatbot implementations and handling long text generation.

Loading preview...

Qwen2.5-1.5B-Instruct Overview

This model is the instruction-tuned 1.54 billion parameter variant from the Qwen2.5 series, building upon the Qwen2 architecture. It incorporates transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings. A key enhancement in Qwen2.5 is its significantly improved capabilities in coding and mathematics, leveraging specialized expert models. It also demonstrates substantial progress in instruction following, generating long texts (up to 8K tokens), and understanding/generating structured data, including JSON.

Key Capabilities

  • Enhanced Coding & Mathematics: Significant improvements due to specialized expert models.
  • Robust Instruction Following: More resilient to diverse system prompts, aiding role-play and chatbot condition-setting.
  • Structured Data Handling: Improved understanding and generation of structured outputs like tables and JSON.
  • Long Context Support: Features a full context length of 32,768 tokens and can generate up to 8,192 tokens.
  • Multilingual Support: Supports over 29 languages, including major global languages like Chinese, English, French, Spanish, and Japanese.

Good For

  • Applications requiring strong coding and mathematical reasoning.
  • Chatbots and agents needing precise instruction following and role-play capabilities.
  • Tasks involving the generation or parsing of structured data, such as JSON.
  • Scenarios demanding long text generation and understanding within a 32K context window.