Qwen 3 4B
Qwen 3 4B is a chat model developed by Qwen, offering capabilities such as function calling, JSON mode, reasoning, streaming, and text generation. It is genuinely best at delivering a comprehensive suite of dense and mixture-of-experts models, with significant enhancements in reasoning capabilities and superior human preference alignment.
Input
Output
Context
41K
Max Output
41K
Parameters
4B
Technical Specifications
Model TypeChat
Context Window40,960 tokens
Max Output Tokens40,960 tokens
Parameters4B
Release DateApr 27, 2025
Training CutoffMar 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.1%
HLE
65.7%
AIME
52.2%
GPQA
3.5%
SciCode
93.3%
MATH 500
69.6%
MMLU Pro
22.3
Math
46.5%
LiveCodeBench
8.4
Intelligence
Resources & Links
Estimated GPU Requirements for Qwen 3 4B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.