Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3 4B

qwen/qwen3-4b

Model weights

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

Modalities

Context

128K

Released

Apr 30, 2025

Knowledge Cutoff

Mar 2025

About Qwen: Qwen3 4B

OpenRouter makes Qwen: Qwen3 4B available through a unified, OpenAI-compatible API using the model ID qwen/qwen3-4b.

Qwen: Qwen3 4B accepts text and returns text. It has a 128,000-token context window.

It was released on April 30, 2025; its knowledge cutoff is March 31, 2025.

More models from Qwen

  • Qwen3.8 27B
  • Qwen3 Reranker 8B
  • Qwen3 ASR 1.7B
ActivityFAQ

Activity

Token volume and request traffic to this model over time.

Frequently asked questions

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation.

Qwen3 4B has a 128,000 token context window.

Qwen3.8 27B, Qwen3.8 2.4T A95B, Qwen3.8 Max and 47 more are other text models from Qwen.

Qwen3 4B was released on April 30, 2025. Its knowledge cutoff is March 31, 2025.