Qualcomm® AI HubAI Hub

Qwen3-4B

State‑of‑the‑art large language model useful on a variety of language understanding and generation tasks.

The Qwen3‑4B is a state‑of‑the‑art multilingual base language model with 4 billion parameters, excelling in language understanding, generation, coding, and mathematics.

Quick StartView README
Not supported

This model is currently not supported on any IoT chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets

Quick Start

1

Install Windows CLI App

Download for Windows ARM
2

Run the Model

Paste into CLI and run the following code.

For application and server integration, see Docs.

Model RepositoryHugging FaceResearch Paper

Technical Details

Response Rate:Rate of response generation after the first response token. Measured on a short prompt with a long response (with thinking); may slow down when using longer context lengths.
Supported languages:100+ languages and dialects.

Applicable Scenarios

  • Dialogue
  • Content Generation
  • Customer Support

License

Model:APACHE-2.0
Terms of Use:Qualcomm® Generative AI usage and limitations

Tags

  • llm
  • generative-ai

Supported IoT Devices

  • Arduino VENTUNO Q
  • Dragonwing IQ-9075 EVK
  • Dragonwing IQ-X5121
  • Dragonwing IQ-X7181
  • Dragonwing Q-8750

Supported IoT Chipsets

  • Qualcomm® QCS5121
  • Qualcomm® Dragonwing™ IQ-X7181
  • Qualcomm® Dragonwing™ IQ-8275
  • Qualcomm® Dragonwing™ Q-8750
  • Qualcomm® Dragonwing™ IQ-9075

Related Models

See all models
View details for the Qwen3-8B model.

Qwen3-8B

State-of-the-art large language model useful on a variety of language understanding and generation tasks.

View details for the Qwen3-4B-Instruct-2507 model.

Qwen3-4B-Instruct-2507

State-of-the-art large language model with instruct-only training, useful on a variety of language understanding and generation tasks.

Looking for more? See models created by industry leaders.

Discover Model Makers