Qwen3

Qwen31. Model Scale2. Performance3. Using Qwen33.1. Running Qwen33.2. Having a Conversation3.3. Ending the Conversation3.4. Chinese ConversationReferences

Note: Due to performance limitations, the RDK X5 4GB version needs to run a small parameter version.

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

1. Model Scale

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 the model. If you have not downloaded this model before, it will be automatically pulled from the Ollama model library:

image-20250628111313072

3.2. Having a Conversation

The response time depends on the hardware configuration, please be patient!

image-20250628112014942

3.3. Ending the Conversation

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

3.4. Chinese Conversation

If you don't have a Chinese input method, you can refer to the tutorial on switching Chinese input methods.

Chinese conversation:

image-20250628112537190

References

Ollama

Official Website: https://ollama.com/

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

Qwen3

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

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