Skip to main content

04-Qwen3

Demo Environment

Development Board : Jetson Orin Series Motherboard

warning

Due to performance limitations, the Jetson Orin Nano 4GB must run the reduced-parameter version

Qwen 3 is the latest generation of large-scale language models in the Qwen series, providing a complete suite of dense and mixture-of-experts (MoE) models.

1. Model Size​

ModelSize
qwen3:0.6b523MB
qwen3:1.7b1.4GB
qwen3:4b2.6GB
qwen3:8b5.2GB

2. Performance​

Evaluation 1

Evaluation 2

3. Using Qwen3​

3.1. Running Qwen3​

Use the run command to start running the model. If you haven't downloaded the model, the model from the Ollama model library will be automatically downloaded:

ollama run qwen3:8b

Screenshot

3.2. Starting a Conversation​

Please tell me how many hours there are in a day.

Response time depends on your hardware configuration, so please be patient!

Screenshot

3.3. Ending the Conversation​

Use the Ctrl+d shortcut or /bye to end the conversation!

References​

Ollama

Official Website: https://ollama.com/

GitHub: https://github.com/ollama/ollama

Qwen3

GitHub: https://github.com/QwenLM/Qwen3

Ollama Model: https://ollama.com/library/qwen3