tangyunbo/Qwen3-4B-RL-multiscope-fromscratch-iter297

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 28, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3-4B-Instruct-2507 is a 4.0 billion parameter causal language model developed by Qwen, featuring significant enhancements in general capabilities including instruction following, reasoning, mathematics, coding, and multilingual knowledge. This model is specifically designed for non-thinking mode operations and excels in long-context understanding up to 262,144 tokens. It offers improved alignment with user preferences for subjective and open-ended tasks, making it suitable for generating high-quality, helpful text and agentic tool-calling applications.

Loading preview...

Overview

Qwen3-4B-Instruct-2507 is an updated 4.0 billion parameter causal language model from Qwen, specifically designed for "non-thinking mode" operations, meaning it does not generate <think></think> blocks. It boasts a native context length of 262,144 tokens, making it highly capable for tasks requiring extensive context understanding.

Key Capabilities & Enhancements

This model demonstrates significant improvements across several domains:

  • General Capabilities: Enhanced instruction following, logical reasoning, text comprehension, mathematics, science, and coding.
  • Multilingualism: Substantial gains in long-tail 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.
  • Agentic Use: Excels in tool-calling capabilities, with recommendations to use Qwen-Agent for optimal performance.

Performance Highlights

Benchmarks show Qwen3-4B-Instruct-2507 outperforming its predecessor and other models in its class across various metrics:

  • Knowledge: Achieves 69.6 on MMLU-Pro and 84.2 on MMLU-Redux.
  • Reasoning: Scores 47.4 on AIME25 and 80.2 on ZebraLogic.
  • Coding: Reaches 35.1 on LiveCodeBench v6 and 76.8 on MultiPL-E.
  • Alignment: Scores 43.4 on Arena-Hard v2 and 83.5 on Creative Writing v3.

When to Use This Model

This model is ideal for developers seeking a compact yet powerful LLM for:

  • Applications requiring extensive context understanding (up to 256K tokens).
  • Tasks demanding strong instruction following and high-quality text generation in open-ended scenarios.
  • Agentic workflows and tool-calling applications where robust performance is crucial.
  • Use cases benefiting from improved multilingual knowledge and reasoning abilities in a 4B parameter model.

Finetunes
1 models