Llama 3.2

Llama 3.21. Model Size2. Performance3. Using Llama 3.23.1 Running Llama 3.23.2 Starting a Conversation3.3 Ending a ConversationReferences

Demo Environment

Development Board: Jetson Orin series motherboard

Note: Due to performance limitations, the Jetson Orin Nano 4GB requires the reduced-parameter version

Meta Llama 3.2 is a series of advanced open-source large-scale language models (LLMs) developed by the Meta AI department.

1. Model Size

ModelSize
llama3.2:1b1.3GB
llama3.2:3b2.0GB

2. Performance

Llama 3.2 instruction-tuned benchmarks

3. Using Llama 3.2

3.1 Running Llama 3.2

Use the run command to run the model. If the model is not already downloaded, it will automatically pull the model from the Olama model library:

image-20250627184454105

3.2 Starting a Conversation

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

image-20250627185035604

3.3 Ending a Conversation

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

References

Ollama

Official Website: https://ollama.com/

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

Llama 3.2

Official Website: https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2/

Ollama Model: https://ollama.com/library/llama3.2