qwen

Qwen/Qwen3-4B

Fine-tunable
text-to-text
Dual reasoning modes enable rapid or step-by-step responses, with robust support for over 100 languages and long-context processing up to 262,144 tokens.
About
Released: 4/29/2025

Qwen/Qwen3-4B is an LLM. It excels in efficient general-purpose dialogue, instruction following, coding, mathematics, and multilingual tasks, while maintaining a compact parameter size suitable for resource-constrained environments.

Some other noteworthy features of Qwen/Qwen3-4B include robust support for over 100 languages and dialects, long-context processing up to 262,144 tokens, and strong performance in both creative writing and technical applications.

MetricValue
Parameter Count4 billion
Mixture of ExpertsNo
Context Length262,144 tokens
MultilingualYes
Quantized*No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.