# Multilingual conversation optimization

Llama 3.1 is a multilingual large language model series developed by Meta, including 8B, 70B, and 405B scales, supporting multilingual text generation and code generation tasks.

Llama 3.2 is a multilingual large language model series developed by Meta, including 1B and 3B scale pre-trained and instruction-tuned generative models, optimized for multilingual conversation scenarios.

Meta Llama 3.1 is a set of pretrained and instruction-tuned generative models with 8B, 70B, and 405B parameters, optimized for multilingual conversation scenarios, supporting 8 languages and code generation.