ManTheMan66/Qwen3-4B-Instruct-2507

TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Apr 15, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

ManTheMan66/Qwen3-4B-Instruct-2507 is a 4 billion parameter instruction-tuned causal language model developed by Qwen, featuring a native context length of 262,144 tokens. This updated Qwen3-4B variant significantly improves general capabilities including instruction following, logical reasoning, mathematics, coding, and long-tail knowledge across multiple languages. It is specifically designed for enhanced alignment with user preferences in subjective and open-ended tasks, making it suitable for generating helpful and high-quality text.

Loading preview...

Qwen3-4B-Instruct-2507: Enhanced Instruction-Following LLM

Qwen3-4B-Instruct-2507 is an updated 4 billion parameter instruction-tuned causal language model from the Qwen3 family, notable for its 262,144 native token context length. This version focuses on a "non-thinking mode," streamlining output without requiring explicit enable_thinking=False settings.

Key Capabilities & Enhancements

  • General Capabilities: Significant improvements across instruction following, logical reasoning, text comprehension, mathematics, science, and coding.
  • Long-Tail Knowledge: Substantial gains in knowledge coverage across multiple languages.
  • User Alignment: Markedly better alignment with user preferences for subjective and open-ended tasks, leading to more helpful responses and higher-quality text generation.
  • Long-Context Understanding: Enhanced capabilities in processing and understanding very long contexts up to 256K tokens.
  • Agentic Use: Excels in tool-calling capabilities, with recommendations to use Qwen-Agent for optimal agentic performance.

Performance Highlights

Benchmarking against previous Qwen3 models and other LLMs, Qwen3-4B-Instruct-2507 shows strong performance:

  • Knowledge: Achieves 69.6 on MMLU-Pro and 62.0 on GPQA, outperforming its predecessor.
  • Reasoning: Scores 47.4 on AIME25 and 80.2 on ZebraLogic, demonstrating significant gains.
  • Coding: Reaches 35.1 on LiveCodeBench v6 and 76.8 on MultiPL-E.
  • Alignment: Achieves 83.4 on IFEval and 83.5 on Creative Writing v3, indicating improved subjective quality.

Recommended Use Cases

This model is particularly well-suited for applications requiring:

  • Advanced instruction following and complex task execution.
  • High-quality text generation in open-ended scenarios.
  • Long-context processing for detailed analysis or summarization.
  • Agentic workflows and tool-use integration.

Finetunes
1 models